---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:
- Qwen/Qwen3.5-35B-A3B-FP8
tags: [vllm_ci]
---

# Model Overview

- **Model Architecture:** Qwen3_5MoeForConditionalGeneration
  - **Input:** Text
  - **Output:** Text
- **Supported Hardware Microarchitecture:** AMD MI300 MI350/MI355
- **ROCm**: 7.0.0
- **PyTorch**: 2.9.1
- **Transformers**: 5.3.0
- **vLLM**: 0.16.0rc2
- **lm-evaluation-harness**: 0.4.11
- **Operating System(s):** Linux
- **Inference Engine:** [SGLang](https://docs.sglang.ai/)/[vLLM](https://docs.vllm.ai/en/latest/)
- **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (v0.12)
  - **Weight quantization:** OCP MXFP4, Static
  - **Activation quantization:** OCP MXFP4, Dynamic


# Model Quantization

The model was quantized from [Qwen/Qwen3.5-35B-A3B-FP8](https://huggingface.co/Qwen/Qwen3.5-35B-A3B-FP8) using [AMD-Quark](https://quark.docs.amd.com/latest/index.html). 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](https://github.com/vllm-project/vllm/tree/v0.19.0rc0) framework.

### Accuracy

<table>
  <tr>
   <td><strong>Benchmark</strong>
   </td>
   <td><strong>Qwen/Qwen3.5-35B-A3B-FP8 </strong>
   </td>
   <td><strong>amd/Qwen3.5-35B-A3B-MXFP4(this model)</strong>
   </td>
   <td><strong>Recovery</strong>
   </td>
  </tr>
  <tr>
   <td>gsm8k (flexible-extract) 
   </td>
   <td>89.39
   </td>
   <td>93.25
   </td>
   <td>104.32%
   </td>
  </tr>
</table>


### Reproduction

The GSM8K results were obtained using the vLLM framework, based on the Docker image [rocm/vllm-dev:nightly_main_20260211], and vLLM is installed inside the container.

docker pull rocm/vllm-dev:nightly_main_20260211

#### Evaluating model in a new terminal
```
lm_eval \
  --model vllm \
  --model_args pretrained=amd/Qwen3.5-35B-A3B-MXFP4,tensor_parallel_size=4,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.