Instructions to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Use Docker

docker model run hf.co/AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Ollama
How to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with Ollama:
```
ollama run hf.co/AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0
```
Unsloth Desktop

How to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with Docker Model Runner:
```
docker model run hf.co/AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0
```

Lemonade

How to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Run and chat with the model

lemonade run user.MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF / kld_data /llm_quantization_data.csv

AMAImedia

Copy files from models/AesSedai/MiMo-V2.6-Flash-MOPD-GGUF

4982964 verified 25 days ago

Raw History Blame Contribute Delete

23.8 kB

model_name,file_size_gb,bpw,Mean KLD_mean,0.01.311.007 I common_memory_breakdown_print,0.01.331.344 I common_memory_breakdown_print,0.01.336.154 I common_params_fit_impl,0.01.336.161 I common_fit_params,0.01.357.243 I common_memory_breakdown_print,0.01.357.644 I llama_model_loader,0.01.357.645 I llama_model_loader,0.01.357.652 I llama_model_loader,0.01.357.673 I llama_model_loader,0.01.357.674 I llama_model_loader,0.01.357.675 I llama_model_loader,0.01.357.676 I llama_model_loader,0.01.357.684 I llama_model_loader,0.01.357.685 I llama_model_loader,0.01.357.686 I llama_model_loader,0.01.357.690 I llama_model_loader,0.01.357.693 I llama_model_loader,0.01.357.884 I common_params_fit_impl,0.01.357.889 I common_fit_params,0.01.375.671 I llama_model_loader,0.01.375.674 I llama_model_loader,0.01.375.675 I llama_model_loader,0.01.375.676 I llama_model_loader,0.01.375.677 I print_info,0.01.380.567 I common_params_fit_impl,0.01.380.573 I common_fit_params,0.01.380.710 I llama_model_loader,0.01.380.711 I llama_model_loader,0.01.380.717 I llama_model_loader,0.01.380.728 I llama_model_loader,0.01.380.729 I llama_model_loader,0.01.380.730 I llama_model_loader,0.01.380.736 I llama_model_loader,0.01.380.737 I llama_model_loader,0.01.380.738 I llama_model_loader,0.01.380.742 I llama_model_loader,0.01.380.745 I llama_model_loader,0.01.401.340 I llama_model_loader,0.01.401.347 I llama_model_loader,0.01.401.359 I llama_model_loader,0.01.401.360 I llama_model_loader,0.01.401.361 I llama_model_loader,0.01.401.367 I llama_model_loader,0.01.401.368 I llama_model_loader,0.01.401.369 I llama_model_loader,0.01.401.374 I llama_model_loader,0.01.401.377 I llama_model_loader,0.01.410.659 I llama_model_loader,0.01.410.663 I llama_model_loader,0.01.410.664 I llama_model_loader,0.01.410.665 I llama_model_loader,0.01.410.667 I print_info,0.01.415.340 I load,0.01.419.540 I llama_model_loader,0.01.419.543 I llama_model_loader,0.01.419.544 I llama_model_loader,0.01.419.545 I print_info,0.01.419.546 I print_info,0.01.425.204 I load,0.01.425.205 I load,0.01.425.206 I load,0.01.425.290 I load,0.01.451.010 I load,0.01.451.029 I print_info,0.01.451.030 I print_info,0.01.451.031 I print_info,0.01.451.040 I print_info,0.01.451.044 I print_info,0.01.451.045 I print_info,0.01.451.047 I print_info,0.01.451.054 I print_info,0.01.451.066 I print_info,0.01.451.067 I print_info,0.01.451.069 I print_info,0.01.451.070 I print_info,0.01.451.071 I print_info,0.01.451.072 I print_info,0.01.451.073 I print_info,0.01.451.074 I print_info,0.01.451.075 I print_info,0.01.451.076 I print_info,0.01.451.077 I print_info,0.01.451.079 I print_info,0.01.451.080 I print_info,0.01.451.081 I print_info,0.01.451.082 I print_info,0.01.459.086 I load,0.01.463.067 I load,0.01.469.209 I load,0.01.469.210 I load,0.01.469.211 I load,0.01.469.288 I load,0.01.472.866 I load,0.01.472.867 I load,0.01.472.868 I load,0.01.472.945 I load,0.01.494.978 I load,0.01.494.994 I print_info,0.01.494.995 I print_info,0.01.494.996 I print_info,0.01.494.997 I print_info,0.01.495.005 I print_info,0.01.495.009 I print_info,0.01.495.010 I print_info,0.01.495.011 I print_info,0.01.495.013 I print_info,0.01.495.019 I print_info,0.01.495.024 I print_info,0.01.495.025 I print_info,0.01.495.026 I print_info,0.01.495.027 I print_info,0.01.495.028 I print_info,0.01.495.029 I print_info,0.01.495.030 I print_info,0.01.495.031 I print_info,0.01.495.032 I print_info,0.01.495.034 I print_info,0.01.495.036 I print_info,0.01.495.037 I print_info,0.01.495.038 I print_info,0.01.495.039 I print_info,0.01.495.040 I print_info,0.01.495.041 I print_info,0.01.498.828 I load,0.01.498.845 I print_info,0.01.498.846 I print_info,0.01.498.847 I print_info,0.01.498.848 I print_info,0.01.498.856 I print_info,0.01.498.860 I print_info,0.01.498.861 I print_info,0.01.498.862 I print_info,0.01.498.864 I print_info,0.01.498.870 I print_info,0.01.498.873 I print_info,0.01.498.874 I print_info,0.01.498.875 I print_info,0.01.498.876 I print_info,0.01.498.877 I print_info,0.01.498.878 I print_info,0.01.498.879 I print_info,0.01.498.880 I print_info,0.01.498.882 I print_info,0.01.498.883 I print_info,0.01.498.884 I print_info,0.01.498.885 I print_info,0.01.498.886 I print_info,0.01.498.887 I print_info,0.01.498.890 I print_info,0.01.498.891 I print_info,0.01.498.892 I print_info,0.01.498.893 I print_info,0.01.498.894 I print_info,0.01.498.895 I print_info,0.02.044.800 I common_memory_breakdown_print,0.02.070.119 I common_params_fit_impl,0.02.070.125 I common_fit_params,0.02.091.431 I llama_model_loader,0.02.091.438 I llama_model_loader,0.02.091.450 I llama_model_loader,0.02.091.451 I llama_model_loader,0.02.091.452 I llama_model_loader,0.02.091.458 I llama_model_loader,0.02.091.459 I llama_model_loader,0.02.091.460 I llama_model_loader,0.02.091.464 I llama_model_loader,0.02.091.468 I llama_model_loader,0.02.109.742 I llama_model_loader,0.02.109.745 I llama_model_loader,0.02.109.746 I llama_model_loader,0.02.109.748 I print_info,0.02.148.667 I load,0.02.158.628 I load,0.02.158.629 I load,0.02.158.630 I load,0.02.158.708 I load,0.02.184.349 I load,0.02.184.367 I print_info,0.02.184.368 I print_info,0.02.184.369 I print_info,0.02.184.384 I print_info,0.02.184.389 I print_info,0.02.184.390 I print_info,0.02.184.391 I print_info,0.02.184.393 I print_info,0.02.184.400 I print_info,0.02.184.403 I print_info,0.02.184.404 I print_info,0.02.184.406 I print_info,0.02.184.407 I print_info,0.02.184.408 I print_info,0.02.184.409 I print_info,0.02.184.410 I print_info,0.02.184.411 I print_info,0.02.184.412 I print_info,0.02.184.413 I print_info,0.02.184.414 I print_info,0.02.184.415 I print_info,0.02.184.416 I print_info,0.02.184.417 I print_info,0.02.184.418 I print_info,0.02.184.420 I print_info,0.02.184.421 I print_info,0.02.184.422 I print_info,0.02.184.423 I print_info,0.02.184.424 I print_info,0.02.184.425 I print_info,0.02.423.138 I common_memory_breakdown_print,0.02.446.660 I common_params_fit_impl,0.02.446.665 I common_fit_params,0.02.467.960 I llama_model_loader,0.02.467.961 I llama_model_loader,0.02.467.967 I llama_model_loader,0.02.467.979 I llama_model_loader,0.02.467.980 I llama_model_loader,0.02.467.981 I llama_model_loader,0.02.467.986 I llama_model_loader,0.02.467.987 I llama_model_loader,0.02.467.988 I llama_model_loader,0.02.467.989 I llama_model_loader,0.02.467.991 I llama_model_loader,0.02.467.994 I llama_model_loader,0.02.467.995 I llama_model_loader,0.02.486.072 I llama_model_loader,0.02.486.073 I llama_model_loader,0.02.486.074 I print_info,0.02.525.758 I load,0.02.536.023 I load,0.02.536.024 I load,0.02.536.025 I load,0.02.536.105 I load,0.02.566.092 I load,0.02.566.115 I print_info,0.02.566.116 I print_info,0.02.566.117 I print_info,0.02.566.118 I print_info,0.02.566.119 I print_info,0.02.566.130 I print_info,0.02.566.136 I print_info,0.02.566.137 I print_info,0.02.566.138 I print_info,0.02.566.141 I print_info,0.02.566.148 I print_info,0.02.566.158 I print_info,0.02.566.159 I print_info,0.02.566.161 I print_info,0.02.566.163 I print_info,0.02.566.165 I print_info,0.02.566.166 I print_info,0.02.566.167 I print_info,0.02.566.168 I print_info,0.02.566.169 I print_info,0.02.566.170 I print_info,0.02.566.171 I print_info,0.02.566.172 I print_info,0.02.566.173 I print_info,0.02.566.176 I print_info,0.02.566.177 I print_info,0.02.566.184 I print_info,0.02.566.185 I print_info,0.02.566.186 I print_info,0.1% KLD,0.1% Δp,0.23.626.710 I load_tensors,0.23.626.715 I load_tensors,0.23.626.716 I load_tensors,0.23.626.717 I load_tensors,0.23.626.718 I load_tensors,0.23.626.719 I load_tensors,0.27.209.453 I llama_context,0.27.209.454 I llama_context,0.27.209.458 I llama_context,0.27.209.459 I llama_context,0.27.212.986 I llama_context,0.27.212.999 I llama_kv_cache_iswa,0.27.213.301 I llama_kv_cache,0.27.213.498 I llama_kv_cache,0.27.213.672 I llama_kv_cache,0.27.213.868 I llama_kv_cache,0.27.214.048 I llama_kv_cache,0.27.214.254 I llama_kv_cache,0.27.214.441 I llama_kv_cache,0.27.214.610 I llama_kv_cache,0.27.214.648 I llama_kv_cache,0.27.214.649 I llama_kv_cache,0.27.214.650 I llama_kv_cache_iswa,0.27.214.934 I llama_kv_cache,0.27.215.239 I llama_kv_cache,0.27.215.510 I llama_kv_cache,0.27.215.798 I llama_kv_cache,0.27.216.071 I llama_kv_cache,0.27.217.282 I llama_kv_cache,0.27.217.546 I llama_kv_cache,0.27.217.853 I llama_kv_cache,0.27.217.890 I llama_kv_cache,0.27.218.588 I resolve_fused_ops,0.27.219.311 I resolve_fused_ops,0.27.219.890 I resolve_fused_ops,0.27.220.454 I resolve_fused_ops,0.27.300.393 I sched_reserve,0.27.300.406 I sched_reserve,0.27.300.407 I sched_reserve,0.27.300.408 I sched_reserve,0.27.300.409 I sched_reserve,0.27.300.410 I sched_reserve,0.27.300.411 I sched_reserve,0.27.300.552 I cmn init,0.29.227.188 I kl_divergence,0.30.495.732 I load_tensors,0.30.495.733 I load_tensors,0.30.495.738 I load_tensors,0.30.495.739 I load_tensors,0.30.495.740 I load_tensors,0.30.495.741 I load_tensors,0.34.984.478 I llama_context,0.34.984.479 I llama_context,0.34.984.483 I llama_context,0.34.984.484 I llama_context,0.34.988.616 I llama_context,0.34.988.631 I llama_kv_cache_iswa,0.34.988.963 I llama_kv_cache,0.34.989.176 I llama_kv_cache,0.34.989.372 I llama_kv_cache,0.34.989.561 I llama_kv_cache,0.34.989.762 I llama_kv_cache,0.34.989.985 I llama_kv_cache,0.34.990.185 I llama_kv_cache,0.34.990.383 I llama_kv_cache,0.34.990.421 I llama_kv_cache,0.34.990.422 I llama_kv_cache,0.34.990.423 I llama_kv_cache_iswa,0.34.990.703 I llama_kv_cache,0.34.991.016 I llama_kv_cache,0.34.991.298 I llama_kv_cache,0.34.991.596 I llama_kv_cache,0.34.991.878 I llama_kv_cache,0.34.996.207 I llama_kv_cache,0.34.996.510 I llama_kv_cache,0.34.996.814 I llama_kv_cache,0.34.996.863 I llama_kv_cache,0.34.997.587 I resolve_fused_ops,0.34.998.316 I resolve_fused_ops,0.34.998.888 I resolve_fused_ops,0.34.999.443 I resolve_fused_ops,0.35.083.846 I sched_reserve,0.35.083.863 I sched_reserve,0.35.083.864 I sched_reserve,0.35.083.865 I sched_reserve,0.35.083.866 I sched_reserve,0.35.083.867 I sched_reserve,0.35.083.868 I sched_reserve,0.35.084.029 I cmn init,0.36.261.810 I kl_divergence,0.38.967.765 I load_tensors,0.38.967.771 I load_tensors,0.38.967.772 I load_tensors,0.38.967.773 I load_tensors,0.38.967.774 I load_tensors,0.40.870.040 I load_tensors,0.40.870.041 I load_tensors,0.40.870.046 I load_tensors,0.40.870.047 I load_tensors,0.40.870.048 I load_tensors,0.40.870.049 I load_tensors,0.44.877.689 I llama_context,0.44.877.690 I llama_context,0.44.877.691 I llama_context,0.44.877.694 I llama_context,0.44.877.695 I llama_context,0.44.881.377 I llama_context,0.44.881.390 I llama_kv_cache_iswa,0.44.881.682 I llama_kv_cache,0.44.881.897 I llama_kv_cache,0.44.882.067 I llama_kv_cache,0.44.882.244 I llama_kv_cache,0.44.882.414 I llama_kv_cache,0.44.882.587 I llama_kv_cache,0.44.882.771 I llama_kv_cache,0.44.882.962 I llama_kv_cache,0.44.882.999 I llama_kv_cache,0.44.883.000 I llama_kv_cache,0.44.883.001 I llama_kv_cache_iswa,0.44.883.303 I llama_kv_cache,0.44.883.577 I llama_kv_cache,0.44.883.869 I llama_kv_cache,0.44.884.158 I llama_kv_cache,0.44.884.428 I llama_kv_cache,0.44.884.726 I llama_kv_cache,0.44.888.289 I llama_kv_cache,0.44.888.655 I llama_kv_cache,0.44.888.703 I llama_kv_cache,0.44.889.440 I resolve_fused_ops,0.44.890.228 I resolve_fused_ops,0.44.890.785 I resolve_fused_ops,0.44.891.337 I resolve_fused_ops,0.44.981.148 I sched_reserve,0.44.981.169 I sched_reserve,0.44.981.171 I sched_reserve,0.44.981.172 I sched_reserve,0.44.981.173 I sched_reserve,0.44.981.174 I sched_reserve,0.44.981.175 I sched_reserve,0.44.981.177 I sched_reserve,0.44.981.326 I cmn init,0.45.463.906 I kl_divergence,0.47.106.207 I llama_context,0.47.106.208 I llama_context,0.47.106.212 I llama_context,0.47.106.213 I llama_context,0.47.110.044 I llama_context,0.47.110.057 I llama_kv_cache_iswa,0.47.110.346 I llama_kv_cache,0.47.110.569 I llama_kv_cache,0.47.110.763 I llama_kv_cache,0.47.110.956 I llama_kv_cache,0.47.111.144 I llama_kv_cache,0.47.111.331 I llama_kv_cache,0.47.111.548 I llama_kv_cache,0.47.111.744 I llama_kv_cache,0.47.111.782 I llama_kv_cache,0.47.111.783 I llama_kv_cache_iswa,0.47.112.042 I llama_kv_cache,0.47.112.310 I llama_kv_cache,0.47.112.583 I llama_kv_cache,0.47.112.882 I llama_kv_cache,0.47.113.147 I llama_kv_cache,0.47.122.882 I llama_kv_cache,0.47.123.158 I llama_kv_cache,0.47.123.467 I llama_kv_cache,0.47.123.506 I llama_kv_cache,0.47.123.507 I llama_kv_cache,0.47.124.158 I resolve_fused_ops,0.47.124.933 I resolve_fused_ops,0.47.125.538 I resolve_fused_ops,0.47.126.088 I resolve_fused_ops,0.47.209.603 I sched_reserve,0.47.209.615 I sched_reserve,0.47.209.616 I sched_reserve,0.47.209.617 I sched_reserve,0.47.209.618 I sched_reserve,0.47.209.619 I sched_reserve,0.47.209.620 I sched_reserve,0.47.209.765 I cmn init,0.49.178.668 I kl_divergence,0.55.169.074 I load_tensors,0.55.169.075 I load_tensors,0.55.169.080 I load_tensors,0.55.169.081 I load_tensors,0.55.169.082 I load_tensors,0.55.169.083 I load_tensors,0.55.169.084 I load_tensors,1.0% KLD,1.0% Δp,1.04.026.522 I llama_context,1.04.026.523 I llama_context,1.04.026.527 I llama_context,1.04.026.528 I llama_context,1.04.030.418 I llama_context,1.04.030.429 I llama_kv_cache_iswa,1.04.030.742 I llama_kv_cache,1.04.030.949 I llama_kv_cache,1.04.031.129 I llama_kv_cache,1.04.031.300 I llama_kv_cache,1.04.031.510 I llama_kv_cache,1.04.031.692 I llama_kv_cache,1.04.031.889 I llama_kv_cache,1.04.032.072 I llama_kv_cache,1.04.032.111 I llama_kv_cache,1.04.032.112 I llama_kv_cache_iswa,1.04.032.417 I llama_kv_cache,1.04.032.701 I llama_kv_cache,1.04.032.979 I llama_kv_cache,1.04.033.285 I llama_kv_cache,1.04.034.551 I llama_kv_cache,1.04.034.858 I llama_kv_cache,1.04.035.135 I llama_kv_cache,1.04.035.455 I llama_kv_cache,1.04.035.500 I llama_kv_cache,1.04.035.501 I llama_kv_cache,1.04.036.231 I resolve_fused_ops,1.04.036.971 I resolve_fused_ops,1.04.037.568 I resolve_fused_ops,1.04.038.107 I resolve_fused_ops,1.04.135.243 I sched_reserve,1.04.135.257 I sched_reserve,1.04.135.258 I sched_reserve,1.04.135.259 I sched_reserve,1.04.135.260 I sched_reserve,1.04.135.261 I sched_reserve,1.04.135.422 I cmn init,1.04.306.884 I kl_divergence,10.0% KLD,10.0% Δp,2.22.732.597 I llama_perf_context_print,2.22.732.601 I llama_perf_context_print,2.22.732.602 I llama_perf_context_print,2.22.732.841 I common_memory_breakdown_print,2.23.653.242 I llama_perf_context_print,2.23.653.245 I llama_perf_context_print,2.23.653.246 I llama_perf_context_print,2.23.653.495 I common_memory_breakdown_print,2.24.125.142 I llama_perf_context_print,2.24.125.147 I llama_perf_context_print,2.24.125.433 I common_memory_breakdown_print,2.29.055.558 I llama_perf_context_print,2.29.055.561 I llama_perf_context_print,2.29.055.562 I llama_perf_context_print,2.29.055.802 I common_memory_breakdown_print,25.0% Δp,3.03.087.864 I llama_perf_context_print,3.03.087.868 I llama_perf_context_print,3.03.088.108 I common_memory_breakdown_print,5.0% KLD,5.0% Δp,75.0% Δp,90.0% KLD,90.0% Δp,95.0% KLD,95.0% Δp,99.0% KLD,99.0% Δp,99.9% KLD,99.9% Δp,"Cor(ln(PPL(Q)), ln(PPL(base)))",Maximum KLD,Maximum Δp,Mean KLD_std,Mean PPL(Q)-PPL(base)_mean,Mean PPL(Q)-PPL(base)_std,Mean PPL(Q)/PPL(base)_mean,Mean PPL(Q)/PPL(base)_std,Mean PPL(Q)_mean,Mean PPL(Q)_std,Mean PPL(base)_mean,Mean PPL(base)_std,Mean ln(PPL(Q)/PPL(base))_mean,Mean ln(PPL(Q)/PPL(base))_std,Mean Δp_mean,Mean Δp_std,Median KLD,Median Δp,Minimum KLD,Minimum Δp,RMS Δp_mean,RMS Δp_std,Same top p_mean,Same top p_std,file_path,file_size_gib,is_self_ref,mixture
MiMo-V2.6-Flash-MOPD-BPW2.0 (aes_sedai),77.38457325568,2.0,0.36558,,,,,-9546330321.0,,,,,,,,,,,,,,,,,,,,105132.773494,0.8,,,,,,,,,,,,-1.0,-6.0,-8.2,-92.3251,-122.3216384,-172.32256,-192.321,-212.322,-262.322048,-302.323,,,,,,,-41.3218,-6114.0,-192.0,3.0,6.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.0,,-128247.0,-151645.0,-151664.0,33.0,,,,,0.9312,2.0,1048576.0,4096.0,51.0,64.0,64.0,192.0,128.0,1.688881688888169e+59,7.681536153615362e+194,0.0,0.0,0.707,256.0,1.0,2.0,1.0,64.0,0.0,310.15,309.77,152576.0,151643.0,151663.0,151664.0,256.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,4e-06,-97.325,5252.0,633.25,9362.32,210572.92,610508.92,74144.89,8192.0,1.0,10000000.0,1.0,9.31,-512.0,40.0,120.0,220.0,320.0,420.0,520.0,620.0,720.0,192.0,128.0,512.0,200.0,1200.0,2240.0,3200.0,4240.0,5200.0,6240.0,740.0,128.0,4.0,4.0,4.0,4.0,3137.12,13137.12,33137.12,63137.12,75473.25,9.0,82.434,48.0,584512819216.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,3.4e-05,-78.418,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.001925,-25.102,,,,,,,,,,,,,,,,-8.15,26004.64,35.0,-9546330321.0,0.000374,-41.059,0.351,0.902835,6.992,1.454982,14.307,3.174748,34.556,6.153982,68.364,90.28,15.865305,98.77,0.001645,1.401276,0.018539,1.272436,0.003421,6.544785,0.04062,5.143508,0.030469,0.240933,0.002688,-5.521,0.046,0.164345,-0.507,-4e-06,-99.995,18.773,0.074,76.348,0.11,kld/MiMo-V2.6-Flash-MOPD/wiki-test-raw/aes_sedai/MiMo-V2.6-Flash-MOPD-BPW2.0.md,72.07,False,
MiMo-V2.6-Flash-MOPD-BPW2.5 (aes_sedai),96.73340092416001,2.5,0.226887,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,-9546330321.0,123580.773494,0.9,-1.0,-6.0,-8.2,-102.321048576,-122.3216384,-192.321,-202.321,-212.322,-262.322048,-302.323,-41.3228,-6114.0,-110.0,3.0,0.0,-128247.0,-151645.0,-151664.0,33.0,0.9312,0.0,1048576.0,51.0,64.0,4.888848888848889e+50,128.0,128.0,1.688881688888169e+59,7.681536153615362e+194,5.121024102410241e+194,0.0,0.0,0.707,16384.0,256.0,1.0,2.0,10000000.0,10000.0,128.0,1048576.0,0.0,310.15,309.77,151387.0,151643.0,151661.0,151664.0,151643.0,256.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,2e-06,-89.048,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,50.0,5252.0,633.25,10274.32,311503.06,74688.89,8192.0,1.0,1.0,1.0,9.31,-512.0,40.0,120.0,220.0,320.0,420.0,520.0,620.0,720.0,192.0,128.0,512.0,200.0,1200.0,2240.0,3200.0,4240.0,5200.0,6240.0,740.0,128.0,4.0,4.0,4.0,4.0,3137.12,23137.12,43137.12,75473.25,321.38,9.0,86.884,48.0,584512819216.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,1.6e-05,-58.876,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.000858,-16.173,,,,,33101.71,108441.36299009,35.0,-9546330321.0,,,,,,,,-4.548,,,,0.000167,-27.207,0.773,0.547494,7.488,0.901214,14.399,2.096844,33.725,4.334219,66.173,94.13,11.077068,99.428,0.001093,0.540957,0.01163,1.105173,0.00226,5.684465,0.034102,5.143508,0.030469,0.100002,0.002045,-2.744,0.036,0.097596,-0.121,-4e-06,-99.531,14.342,0.064,81.14,0.101,kld/MiMo-V2.6-Flash-MOPD/wiki-test-raw/aes_sedai/MiMo-V2.6-Flash-MOPD-BPW2.5.md,90.09,False,
MiMo-V2.6-Flash-MOPD-BPW3.0 (aes_sedai),116.13591568384,3.0,0.173319,-9546330321.0,,141878.773494,0.81,,-0.2,-1.0,-6.0,-8.2,-92.3251,-102.321048576,-122.3216384,-182.328,-202.321,-212.322,-262.322048,-302.323,,,-41.3223,-80119.0,-270.0,-45.0,3.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.0,,,,,,-128247.0,-151662.0,-151664.0,33.0,0.9312,0.0,1048576.0,51.0,64.0,0.0,128.0,1.688881688888169e+59,7.681536153615362e+194,5.121024102410241e+194,0.0,0.0,0.707,256.0,2.0,10000000.0,10000.0,0.0,310.15,309.77,152576.0,198.0,151643.0,256.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.0,-82.502,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,5252.0,633.25,114880.63,416036.29,75579.27,,,,,,,16.0,8192.0,1.0,10000000.0,1.0,9.31,-512.0,40.0,120.0,220.0,320.0,420.0,520.0,620.0,720.0,192.0,128.0,512.0,200.0,1200.0,2240.0,3200.0,4240.0,5200.0,6240.0,740.0,128.0,4.0,4.0,4.0,4.0,3137.12,13137.12,33137.12,53137.12,63137.12,75473.25,9.0,92.354,48.0,584512819216.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,1e-05,-48.258,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.000547,-12.569,,,,,,,,,,,,43734.93,103944.53299009,35.0,-9546330321.0,-3.336,,,,0.000106,-21.391,0.906,0.419454,7.341,0.693451,14.169,1.630818,33.953,3.507959,64.389,95.69,9.484143,99.318,0.00087,0.282012,0.009365,1.054829,0.001837,5.42552,0.032234,5.143508,0.030469,0.053378,0.001741,-1.644,0.032,0.071906,-0.051,-4e-06,-99.219,12.411,0.059,83.395,0.096,kld/MiMo-V2.6-Flash-MOPD/wiki-test-raw/aes_sedai/MiMo-V2.6-Flash-MOPD-BPW3.0.md,108.16,False,
MiMo-V2.6-Flash-MOPD-BPW3.5 (aes_sedai),135.48474335232,3.5,0.134408,,-9546330321.0,,,,,,,,,,,,,,,,160326.773494,0.81,,,,,,,,-0.2,-1.0,-6.0,-8.2,-92.3251,-122.3216384,-172.32256,-202.321,-212.322,-262.322048,-302.323,,,,,,,,,,,-41.323,-32248.0,-382.0,-442.0,3.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.0,,,,,-128247.0,-151645.0,-151664.0,33.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.9312,2.0,1048576.0,4096.0,51.0,64.0,4.888848888848889e+50,192.0,128.0,1.688881688888169e+59,7.681536153615362e+194,5.121024102410241e+194,0.0,0.0,0.0,0.707,256.0,1.0,2.0,1.0,1.0,1048576.0,0.0,310.15,309.77,11.0,151643.0,151660.0,151643.0,151664.0,256.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.0,-72.473,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,50.0,5252.0,633.25,117136.63,516528.63,76331.27,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,512.0,1.0,10000000.0,1.0,9.31,-512.0,40.0,120.0,220.0,320.0,420.0,520.0,620.0,720.0,128.0,512.0,200.0,1200.0,2240.0,3200.0,4240.0,5200.0,6240.0,740.0,192.0,128.0,4.0,4.0,4.0,4.0,3137.12,23137.12,53137.12,75473.25,321.38,9.0,86.024,48.0,584512819216.0,,,,,,,,6e-06,-39.103,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.000344,-9.886,45924.73,95396.80299009,35.0,-9546330321.0,,,,,,,,,,,,-2.292,,,,6.4e-05,-17.032,1.131,0.323517,7.458,0.539768,13.893,1.280194,33.297,2.925446,63.722,96.67,8.01248,98.582,0.000692,0.104501,0.007963,1.020317,0.00156,5.248009,0.031054,5.143508,0.030469,0.020113,0.001529,-0.734,0.028,0.055338,-0.005,-4e-06,-99.62,10.91,0.054,85.148,0.092,kld/MiMo-V2.6-Flash-MOPD/wiki-test-raw/aes_sedai/MiMo-V2.6-Flash-MOPD-BPW3.5.md,126.18,False,
MiMo-V2.6-Flash-MOPD-MXFP4 (aes_sedai),174.90180571136,4.52,-0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,-151311920321.0,196480.773494,1.04,-0.2,-1.0,-6.0,-8.2,-92.3251,-122.3216384,-172.32256,-202.321,-212.322,-24.3238,-272.322048,-312.323,-32.322,-32248.0,-4141.0,4.0,0.0,-128247.0,-151645.0,-151664.0,33.0,0.9312,2.0,0.0,1048576.0,4096.0,51.0,64.0,4.888848888848889e+50,128.0,128.0,1.688881688888169e+59,7.681536153615362e+194,5.121024102410241e+194,0.0,0.0,0.707,256.0,-1.0,2.0,10000000.0,1.0,1048576.0,0.0,310.15,309.77,11.0,151645.0,151643.0,151664.0,256.0,-5.2e-05,-0.004,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,50.0,5252.0,1192.0,21232.23,320678.19,624126.23,78078.08,-3.8e-05,-0.002,512.0,1.0,1.0,1.0,9.31,-512.0,40.0,120.0,220.0,320.0,420.0,520.0,620.0,720.0,128.0,512.0,200.0,1200.0,2240.0,3200.0,4240.0,5200.0,6240.0,740.0,192.0,128.0,4.0,4.0,4.0,4.0,3137.12,23137.12,53137.12,75473.25,9.0,99.674,48.0,584512819216.0,-1.5e-05,-0.0,,,,,,,,,61804.77,35.0,-151311920321.0,,,,,0.0,,,,-2.3e-05,-0.001,0.0,1.5e-05,0.0,2.3e-05,0.001,3.7e-05,0.002,5.1e-05,0.004,99.96,6.7e-05,0.006,0.0,0.003874,0.000817,1.000753,0.000158,5.147382,0.030566,5.143508,0.030469,0.000753,0.000158,0.0,0.0,-0.0,0.0,-6.5e-05,-0.006,0.001,0.0,99.997,0.001,kld/MiMo-V2.6-Flash-MOPD/wiki-test-raw/aes_sedai/MiMo-V2.6-Flash-MOPD-MXFP4.md,162.89,False,