Qwen3.8-Flash-Next-NVFP4: NVFP4 routed experts + FP8 PLE (135GB)

NVFP4 W4A4 quantization of the 48 routed-expert MoE layers of
Qwen/Qwen3.8-Flash-Next (Model Optimizer snapshot 87c9f8cf, group 16);
PLE n-gram embedding tables in FP8 from Qwen/Qwen3.8-Flash-Next-FP8;
all other tensors BF16 source-identical. GSM8K 97.27%, AIME26 pass@1
98.75% (previous PLE revision). Full integrity evidence included.

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,150 @@
+---
+pipeline_tag: image-text-to-text
+base_model:
+- Qwen/Qwen3.8-Flash-Next
+license: other
+library_name: Model Optimizer
+tags:
+- ModelOpt
+- Qwen3.8
+- quantized
+- FP4
+- fp4
+- sglang
+---
+
+# Model Overview
+
+## Description:
+RadixArk Qwen3.8-Flash-Next-NVFP4 is the quantized version of
+[Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next),
+a hybrid-architecture multimodal Mixture-of-Experts model. Quantization was
+performed with [NVIDIA Model Optimizer](https://github.com/NVIDIA/TensorRT-Model-Optimizer)
+(snapshot `87c9f8cf`) using the NVFP4 W4A4 recipe, scoped to the routed
+experts only.
+
+This checkpoint is a private candidate release.
+
+## References
+NVIDIA Model Optimizer: https://github.com/NVIDIA/TensorRT-Model-Optimizer
+
+### License/Terms of Use:
+See the [source model](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) for
+license terms.
+
+### Use Case:
+Developers evaluating NVFP4-quantized serving of Qwen3.8-Flash-Next for
+agentic systems, chat, coding, and multimodal reasoning workloads.
+
+### Release Date:
+Hugging Face on 08/25/2026 via https://huggingface.co/RadixArk/Qwen3.8-Flash-Next-NVFP4
+
+## Model Architecture:
+**Architecture Type:** Transformer (hybrid GDN + QSA sparse attention,
+multi-hyperconnection streams, PLE n-gram injection) <br>
+**Network Architecture:** Multimodal MoE — 48 decoder layers, 512 routed
+experts per MoE layer (top-10 routing) + shared expert, 1 MTP layer <br>
+**Number of Model Parameters:** ~180B in total (360 GB BF16 source) <br>
+
+## Input:
+**Input Type(s):** Text, Image, Video <br>
+**Input Format(s):** String, RGB, Video <br>
+**Other Properties Related to Input:** Context length up to 262K <br>
+
+## Output:
+**Output Type(s):** Text <br>
+**Output Format:** String <br>
+
+## Software Integration:
+**Supported Runtime Engine(s):** <br>
+* SGLang (with `qwen4_exp` model support) <br>
+
+**Supported Hardware Microarchitecture Compatibility:** <br>
+* NVIDIA Blackwell (validated on GB300 and B300) <br>
+
+**Preferred Operating System(s):** <br>
+* Linux <br>
+
+## Model Version(s):
+NVFP4 candidate 1.0, quantized with nvidia-modelopt v0.46.0 (snapshot
+`87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c`).
+
+## Calibration Dataset:
+**Link:** [cnn_dailymail](https://huggingface.co/datasets/abisee/cnn_dailymail)
+(config 3.0.0, train split) <br>
+**Properties:** 128 articles (seed 1234), truncated to 512 tokens; MoE-block
+input activations captured from live SGLang serving (prefill only),
+62,139 rows per layer; activation scales by max calibration over 8 seeded
+sampled batches per part. Representativeness probe: GSM8K train [0:16] x2. <br>
+
+## Post Training Quantization
+This model was obtained by quantizing Qwen3.8-Flash-Next to NVFP4, ready for
+inference with SGLang. **Only the routed experts of the 48 main-model MoE
+layers are quantized** (fused `gate_up_proj` / `down_proj`; 294,912 quantized
+tensor entries) to NVFP4 W4A4 (E2M1, group size 16, FP8 E4M3 block scales,
+FP32 global scales, dynamic NVFP4 activations). Attention, QSA, GDN, mHC,
+shared experts, routers, embeddings, LM head, vision, and **all 31 MTP
+tensors remain BF16 and byte-identical to the source**. **The PLE n-gram
+embedding tables use the FP8-quantized versions from the updated
+`Qwen/Qwen3.8-Flash-Next-FP8` revision** (128 shards F8_E4M3 + per-table
+scalar scale, dequantized to BF16 at load time); the remaining PLE weights
+stay BF16. No KV-cache quantization metadata. Checkpoint size is reduced
+from 360 GB to 135 GB (~2.7x).
+
+## Usage
+
+Serve with SGLang (requires a build with `qwen4_exp` support):
+
+```sh
+python -m sglang.launch_server \
+  --model-path RadixArk/Qwen3.8-Flash-Next-NVFP4 \
+  --tp 2 \
+  --quantization modelopt_fp4 \
+  --fp4-gemm-backend flashinfer_cutlass \
+  --page-size 64 \
+  --mamba-scheduler-strategy extra_buffer \
+  --mamba-track-interval 64 \
+  --chunked-prefill-size 4096 \
+  --max-running-requests 36 \
+  --context-length 262144 \
+  --mem-fraction-static 0.80 \
+  --allow-auto-truncate \
+  --port 30000
+```
+
+## Evaluation
+Results attributed to this exact checkpoint unless noted otherwise:
+
+| Eval | Protocol | BF16 reference¹ | NVFP4 (this checkpoint) |
+|---|---|---|---|
+| GSM8K | full 1319, t0.6 / top-p 0.95 / max 8192 | 97.12–97.50² | **97.27** (stop 98.86, err 0) |
+| AIME26 | 30 problems x 8, t1.0 / max 130k | 100 (240/240) | **98.75 pass@1** (majority@8 100, stop 99.17) ³ |
+
+¹ BF16 reference runs were recorded on an earlier checkpoint revision of the
+same model line; the two revisions' weight deltas are not established, so
+treat comparisons as indicative, not exact.
+² Range across three independent BF16 runs on the earlier revision.
+³ Measured on the previous revision of this checkpoint, whose weights differ
+from the current revision only in the PLE embedding tables.
+
+**Behavioral note:** this quantization preserves single-turn accuracy
+(GSM8K/AIME in-band); long agentic generations tend to run longer than BF16.
+
+## Integrity Evidence
+All audits pass on this exact checkpoint: structural audit (294,912 routed +
+1,562 unchanged + 31 MTP tensors), scale audit (221,184 finite positive
+scales, min 2.13e-05, max 448.0), unchanged-content byte-equality audit
+(1,562 tensors / 118.4 GB), deterministic serving smoke. Raw metrics:
+`gsm8k_metrics.json`, `aime26_metrics.json`;
+audit reports and details: `qualification-notes.md`,
+`validate_checkpoint_report.json`, `validate_scales_report.json`,
+`audit_unchanged_report.json`.
+
+## Model Limitations:
+The base model was trained on data that contains toxic language and societal
+biases originally crawled from the internet. Therefore, the model may amplify
+those biases and return toxic responses especially when prompted with toxic
+prompts. The model may generate answers that may be inaccurate, omit key
+information, or include irrelevant or redundant text producing socially
+unacceptable or undesirable text, even if the prompt itself does not include
+anything explicitly offensive.

aime26_metrics.json

@@ -0,0 +1,41 @@
+{
+  "aggregate": {
+    "error_rate": 0.0,
+    "majority@8": 1.0,
+    "no_answer": 0.004166666666666667,
+    "pass@1": 0.9875,
+    "pass@1_sem": 0.0060993754559283304,
+    "pass@1_std": 0.017251638983558852,
+    "pass@8": 1.0,
+    "score": 0.9875,
+    "stop_rate": 0.9916666666666667,
+    "truncated_rate": 0.008333333333333333
+  },
+  "base_url": "http://127.0.0.1:30000/v1",
+  "gen": {
+    "chat_template_kwargs": {
+      "thinking": true
+    },
+    "extra_body": null,
+    "max_tokens": 130000,
+    "min_p": 0.0,
+    "reasoning_effort": null,
+    "repetition_penalty": 1.0,
+    "seed": 0,
+    "system_message": null,
+    "temperature": 1.0,
+    "top_p": 0.95
+  },
+  "latency_seconds": 11196.289524045998,
+  "model": "qwen38next-nvfp4",
+  "n_repeats": 8,
+  "name": "aime26",
+  "ns_commit_sha": "645cf567ff08c0ae9cc3fc8e1edbb975b3067816",
+  "num_examples": 30,
+  "num_threads": 8,
+  "output_throughput_tps": 440.48262501681074,
+  "sgl_eval_version": "0.0.1",
+  "timestamp": "20260825-064808",
+  "total_completion_tokens": 4931771,
+  "total_prompt_tokens": 48104
+}

audit_unchanged_report.json

@@ -0,0 +1,6 @@
+{
+  "unchanged_compared": 1562,
+  "unchanged_bytes": 118408052728,
+  "mtp_compared": 31,
+  "verdict": "pass"
+}

chat_template.jinja

@@ -0,0 +1,170 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + content + '<|im_end|>\n' }}
+        {%- elif reasoning_instructions %}
+            {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+        {%- endif %}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,197 @@
+{
+  "architectures": [
+    "Qwen4ExpForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen4_exp",
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens",
+      "mtp.*",
+      "model.mtp.*",
+      "*.self_attn.*",
+      "*.linear_attn.*",
+      "*.mlp.gate*",
+      "*.mlp.shared_expert.*",
+      "*.mlp.shared_expert_gate*",
+      "*hyper_connection*",
+      "*.ple.*",
+      "model.visual.*",
+      "model.language_model.embed_tokens",
+      "lm_head"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "hc_count": 4,
+    "hc_lowrank": 320,
+    "head_dim": 256,
+    "heads_per_ngram": 8,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "indexer_budget": 2048,
+    "indexer_compress_ratio": 4,
+    "indexer_head_dim": 128,
+    "indexer_kv_heads": 1,
+    "indexer_n_heads": 4,
+    "initializer_range": 0.02,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 48,
+    "linear_value_head_dim": 128,
+    "make_ngram_vocab_size_divisible_by": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen4_exp_text",
+    "moe_intermediate_size": 640,
+    "mtp": {
+      "hybrid": true,
+      "layer_types": [
+        "full_attention"
+      ],
+      "mtp_use_hidden_state_from_layer": null,
+      "num_hidden_layers": 1,
+      "rope_theta": 10000000
+    },
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "ngram_size": 3,
+    "ngram_vocab_size_base": 20000000,
+    "num_attention_heads": 24,
+    "num_experts": 512,
+    "num_experts_per_tok": 10,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 2,
+    "output_gate_type": "sigmoid",
+    "output_router_logits": false,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "ple_conv_kernel_size": 4,
+    "ple_embed_dim": 2560,
+    "ple_layer_ids": [
+      2
+    ],
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "router_aux_loss_coef": 0.001,
+    "shared_expert_intermediate_size": 640,
+    "split_ngram_parts": 128,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320,
+    "ple_embedding_dtype": "float8_e4m3fn"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0.dev0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen4_exp",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

conversion_environment.json

@@ -0,0 +1,13 @@
+{
+  "accelerate": "1.14.0",
+  "cuda": "13.0",
+  "datasets": "5.0.1",
+  "modelopt_clean": true,
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "modelopt_distribution": "nvidia-modelopt",
+  "modelopt_version": "0.46.0",
+  "python": "3.12.3",
+  "pytorch": "2.13.0+cu130",
+  "safetensors": "0.8.0",
+  "transformers": "5.12.1"
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95
+}

gsm8k_metrics.json

@@ -0,0 +1,33 @@
+{
+  "aggregate": {
+    "error_rate": 0.0,
+    "score": 0.9727065959059894,
+    "stop_rate": 0.9886277482941622,
+    "truncated_rate": 0.011372251705837756
+  },
+  "base_url": "http://127.0.0.1:30001/v1",
+  "gen": {
+    "chat_template_kwargs": null,
+    "extra_body": null,
+    "max_tokens": 8192,
+    "min_p": 0.0,
+    "reasoning_effort": null,
+    "repetition_penalty": 1.0,
+    "seed": 0,
+    "system_message": null,
+    "temperature": 0.6,
+    "top_p": 0.95
+  },
+  "latency_seconds": 829.4909560070373,
+  "model": "qwen38next-nvfp4-plefp8",
+  "n_repeats": 1,
+  "name": "gsm8k",
+  "ns_commit_sha": "645cf567ff08c0ae9cc3fc8e1edbb975b3067816",
+  "num_examples": 1319,
+  "num_threads": 16,
+  "output_throughput_tps": 687.4095442158896,
+  "sgl_eval_version": "0.0.1",
+  "timestamp": "20260826-083046",
+  "total_completion_tokens": 570200,
+  "total_prompt_tokens": 179677
+}

hf_quant_config.json

@@ -0,0 +1,25 @@
+{
+  "producer": {
+    "name": "modelopt",
+    "version": "0.46.0"
+  },
+  "quantization": {
+    "exclude_modules": [
+      "model.embed_tokens",
+      "mtp.*",
+      "model.mtp.*",
+      "*.self_attn.*",
+      "*.linear_attn.*",
+      "*.mlp.gate*",
+      "*.mlp.shared_expert.*",
+      "*.mlp.shared_expert_gate*",
+      "*hyper_connection*",
+      "*.ple.*",
+      "model.visual.*",
+      "model.language_model.embed_tokens",
+      "lm_head"
+    ],
+    "group_size": 16,
+    "quant_algo": "NVFP4"
+  }
+}

layer-00000-experts-0000-0127.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    0,
+    128
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 0,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "0ac37cbedf1a8c6c4f9838500399bf77a4292649baa60df1a2fca446fc69724f",
+  "output_size": 354075168,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00000-experts-0000-0127.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d367f9ed6570543e49a99db0a8f88fe12ed94117f9bb3db0d90624937cb56457
+size 354098208

layer-00000-experts-0128-0255.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    128,
+    256
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 0,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "b402b6bbf71176ea630ff3ebff6f012062effe9884d3fb0d203be8acf1a5721b",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00000-experts-0128-0255.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24ede1ac5e0341608da8ada2989bc92981ff6286e2f1601025ccb8c8d8b36ee
+size 354099528

layer-00000-experts-0256-0383.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    256,
+    384
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 0,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "23adf1ec6cf108474eb393ecd89371efa66a851d69c05ac00af8afb9afdae9f8",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00000-experts-0256-0383.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab7f14e3072a3073079701c721c05aca111c365336294d9eb78651355565bd3
+size 354099528

layer-00000-experts-0384-0511.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    384,
+    512
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 0,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "dfdbe7c9814f9bd8690894e6137ef46330b87dab3a0705473ab31c543532e8d4",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00000-experts-0384-0511.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d91a60f90dbc44655c37d97d7eb37c93d5a8a872b92efed20f77d0705277045
+size 354099528

layer-00001-experts-0000-0127.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    0,
+    128
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 1,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "bda2dc2dcfb2c93cd4a1cbed9203201cbbf7c02fc76579eaec163c024fdcbb47",
+  "output_size": 354075168,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00001-experts-0000-0127.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f987d5b4bf0a09f933e77230a7155917caeccd684a9c2af65ae055e7ba2f5841
+size 354098208

layer-00001-experts-0128-0255.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    128,
+    256
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 1,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "c5394fbed9d0bf80b7fc67d7863d6df34e5e58ef3c3358b5901b7eed241f980a",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00001-experts-0128-0255.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfd3aa965124674ef499f5e33e842ef6e012755dfa659da1e09a2f689a3257d
+size 354099528

layer-00001-experts-0256-0383.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    256,
+    384
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 1,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "065a3fceb73e32644195a430b20e2370ba4379298a26bd80d7e2c11280f1d6f1",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00001-experts-0256-0383.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e38e9e9a79a96cad1473f129897ff2fa79593b65cc9dd1d7416370b96675040
+size 354099528

layer-00001-experts-0384-0511.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    384,
+    512
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 1,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "b6946721baf07acfc4c538a0fcfd07a51392561b4a3871ff210a2f4d957267c6",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00001-experts-0384-0511.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f277f27504d22712822fb711071a212dd695841c9cbf4be7d3719d78f64d3db
+size 354099528

layer-00002-experts-0000-0127.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    0,
+    128
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 2,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "bd453f47991175249ce5bdc61fb790a1f16a77763e98edd1fbf7a497dd56b045",
+  "output_size": 354075168,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00002-experts-0000-0127.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50f19bc1547c83a18d278b5b7c1cb544d76ee1a9487ee16be6e2af7a5135244
+size 354098208

layer-00002-experts-0128-0255.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    128,
+    256
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 2,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "7c2bb9b39e38874fa33f2becd00621ef21eb3ca216401178d918c86349a0f57f",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00002-experts-0128-0255.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76671caa9d6bef00bdead734b3b325aa08091ba3ff10df802ab3a8299cb4380e
+size 354099528

layer-00002-experts-0256-0383.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    256,
+    384
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 2,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "2cd7e8c074d7b3001277a97d283b0a673a3de15a439896a21a9dc54635e11f7c",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00002-experts-0256-0383.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21170bf6d48641a8deb3b72c91a92386361ac15071cb96bc8c3ec60dd4c1428c
+size 354099528

layer-00002-experts-0384-0511.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    384,
+    512
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 2,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "4c0d043d6e05bb59abb8fe2c61c9b838c4ce84b1dca486b335e41d24e4a750b4",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00002-experts-0384-0511.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc02c5de9f8be6cc33c8b9426022ab3af2e8de71665d75b49863e3c4243fd3f6
+size 354099528

layer-00003-experts-0000-0127.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    0,
+    128
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 3,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "9a436059eafd9119f41fcf4985db0d862d94f26774c73913c321aa694ead99a5",
+  "output_size": 354075168,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00003-experts-0000-0127.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a41d71d0405ce057ea78c81fe967cda0e4df89b70eca587306798007aae674
+size 354098208

layer-00003-experts-0128-0255.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    128,
+    256
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 3,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "90f03bf3846affea237f3a74061cf16bba5c6fc86ba1b3cded647c9832b05520",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00003-experts-0128-0255.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d153729652cba5f9f33eb5f7cbc4c2696453d5d7c125b451a5b04319cf8c02
+size 354099528

layer-00003-experts-0256-0383.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    256,
+    384
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 3,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "aa50ccb55772ba8db52fdae7a8c21040dd23c7db48f791e3122aa876205fb090",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00003-experts-0256-0383.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000bb3a3a9148a08cd12ecfb308fc9dc565026aff9fa3f6a39e300a91d21e463
+size 354099528

layer-00003-experts-0384-0511.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    384,
+    512
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 3,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "a16f1c45e87454acd6a0400af11c59b419238b5ede64b319de8091e52f431806",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00003-experts-0384-0511.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27cb3b27f029ec5c18d78cea549f7939336894c2ae01b0b4c174626f639201b
+size 354099528

layer-00004-experts-0000-0127.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    0,
+    128
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 4,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "05b5a3d5b9fb0e3b29cea7fefd2b0bf096b7d6d6bf76c71b7679fde4b72760dd",
+  "output_size": 354075168,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00004-experts-0000-0127.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e784a5b42e35615d3f2eb8ab264ab6d1498e3e8791076b3b0a1c34f3eac9c8c6
+size 354098208

layer-00004-experts-0128-0255.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    128,
+    256
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 4,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "6292f7cbf49b01607831f36bdec1ab2ea4bb30c7df9d19e96f4641715b8f2e3d",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00004-experts-0128-0255.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2479cc9a39ff2648f9c225ade0ce635ab7393662793f7097ff0f502a9b0e44b2
+size 354099528

layer-00004-experts-0256-0383.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    256,
+    384
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 4,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "f73819f3e4464a2df5a924c4414fa6f07b70d6dd197eefc65a0f92aaf7b4879f",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00004-experts-0256-0383.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4926bf02da40ce2adfb2c2e06325b81340d91589aa7c383a8d047bc499c8f573
+size 354099528

layer-00004-experts-0384-0511.complete.json

@@ -0,0 +1,252 @@
+{
+  "calibration_contract": {
+    "activation_pool_rows": 62139,
+    "base_seed": 1234,
+    "batch_seed": "base_seed + layer * 16 + batch",
+    "batch_size": 1,
+    "batches_per_part": 8,
+    "capture_dataset": "cnn_dailymail train (abisee/cnn_dailymail 3.0.0)",
+    "capture_manifest_sha256": "5c2a769728dde49a592036768c8efad1d0488b1342a36ca46f1a5eff0a52727f",
+    "capture_samples": 128,
+    "capture_seed": 1234,
+    "capture_seq_len": 512,
+    "hidden_state_source": "sglang port forward pre-hook on each MoE block input, tp=2 rank0, prefill only",
+    "model_seed": "base_seed + layer",
+    "sequence_length": 512,
+    "type": "captured_real_activations"
+  },
+  "expert_range": [
+    384,
+    512
+  ],
+  "exported_quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        },
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "type": "float"
+        }
+      }
+    },
+    "ignore": [
+      "model.embed_tokens"
+    ],
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quant_algo": "NVFP4",
+    "quant_method": "modelopt"
+  },
+  "layer": 4,
+  "legacy_quantization_config": {
+    "producer": {
+      "name": "modelopt",
+      "version": "0.46.0"
+    },
+    "quantization": {
+      "exclude_modules": [
+        "model.embed_tokens"
+      ],
+      "group_size": 16,
+      "kv_cache_quant_algo": null,
+      "quant_algo": "NVFP4"
+    }
+  },
+  "modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
+  "output_sha256": "06c3e95bc1bc721ff9cc40bc155ea0b5afa857ca037cfc154b76bd142593b050",
+  "output_size": 354076488,
+  "quantization_recipe": {
+    "algorithm": "max",
+    "quant_cfg": [
+      {
+        "enable": false,
+        "quantizer_name": "*"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*block_sparse_moe*input_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*weight_quantizer"
+      },
+      {
+        "cfg": {
+          "block_sizes": {
+            "-1": 16,
+            "scale_bits": [
+              4,
+              3
+            ],
+            "type": "dynamic"
+          },
+          "effective_bits": 4.5,
+          "num_bits": [
+            2,
+            1
+          ]
+        },
+        "quantizer_name": "*.experts.*input_quantizer"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*block_sparse_moe.gate*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_a*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*linear_attn.in_proj_b*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*lm_head*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mixer.conv1d*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mlp.shared_expert_gate.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*output_layer*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*proj_out.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*router*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "output.*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*embed_vision*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_tower*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*visual*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*vision_model*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*multi_modal_projector*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm1d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm2d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.BatchNorm3d",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.LeakyReLU",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "parent_class": "nn.Embedding",
+        "quantizer_name": "*"
+      },
+      {
+        "enable": false,
+        "quantizer_name": "*mtp*"
+      }
+    ]
+  },
+  "reference_config_sha256": "11a62dc500ac8575f281019a9468ddb3114e75729874cfc5fd5115ee3b32a0ae",
+  "source_config_sha256": "889658f2508e8c61d409b02e70e0d78d8d4452ec65aaafbe129805d213d2e74b",
+  "source_index_sha256": "99e815241ef03325536b0aaa4441deea45174c17fae31e10f0bb456410c590de",
+  "tensor_entries": 1536
+}

layer-00004-experts-0384-0511.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05a14cd5e08b38074b35b39e4c961402827d3b9e4737df4b76fc338483859ab
+size 354099528