amd/Qwen3.5-35B-A3B-MXFP4

Model Overview

• Model Architecture: Qwen3_5MoeForConditionalGeneration
  • Input: Text
  • Output: Text
• Supported Hardware Microarchitecture: AMD MI300 MI350/MI355
• ROCm: 7.0
• PyTorch: 2.8.0
• Transformers: 5.2.0
• Operating System(s): Linux
• Inference Engine: SGLang/vLLM
• Model Optimizer: AMD-Quark (v0.11.1)
  • Weight quantization: OCP MXFP4, Static
  • Activation quantization: OCP MXFP4, Dynamic

Model Quantization

The model was quantized from Qwen/Qwen3.5-35B-A3B-FP8 using AMD-Quark. The weights are quantized to MXFP4 and activations are quantized to MXFP4.

Quantization scripts:

cd Quark/examples/torch/language_modeling/llm_ptq/
export exclude_layers="lm_head  model.visual.*  mtp.*  *mlp.gate *shared_expert_gate* *.linear_attn.*  *.self_attn.*  *.shared_expert.*"
python3 quantize_quark.py --model_dir Qwen/Qwen3.5-35B-A3B-FP8 \
                          --quant_scheme  mxfp4 \
                          --file2file_quantization \
                          --exclude_layers $exclude_layers \
                          --output_dir amd/Qwen3.5-35B-A3B-MXFP4

For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.

Evaluation

The model was evaluated on gsm8k benchmarks using the vllm framework.

Accuracy

Benchmark	Qwen/Qwen3.5-35B-A3B	amd/Qwen3.5-35B-A3B-MXFP4(this model)	Recovery
gsm8k (flexible-extract)	90.52	89.23	98.57%

Reproduction

The GSM8K results were obtained using the vLLM framework, based on the Docker image rocm/vllm-dev:nightly, and vLLM is installed inside the container with fixes applied for model support.

Evaluating model in a new terminal

lm_eval \
  --model vllm \
  --model_args pretrained=$MODEL,tensor_parallel_size=1,max_model_len=262144,gpu_memory_utilization=0.90,max_gen_toks=2048,trust_remote_code=True,reasoning_parser=qwen3 \
  --tasks gsm8k  --num_fewshot 5 \
  --batch_size auto

License

Modifications Copyright(c) 2026 Advanced Micro Devices, Inc. All rights reserved.