Instructions to use amd/Qwen3.5-397B-A17B-MoE-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/Qwen3.5-397B-A17B-MoE-MXFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="amd/Qwen3.5-397B-A17B-MoE-MXFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("amd/Qwen3.5-397B-A17B-MoE-MXFP4")
model = AutoModelForMultimodalLM.from_pretrained("amd/Qwen3.5-397B-A17B-MoE-MXFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amd/Qwen3.5-397B-A17B-MoE-MXFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/Qwen3.5-397B-A17B-MoE-MXFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Qwen3.5-397B-A17B-MoE-MXFP4",
		"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/amd/Qwen3.5-397B-A17B-MoE-MXFP4

SGLang

How to use amd/Qwen3.5-397B-A17B-MoE-MXFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "amd/Qwen3.5-397B-A17B-MoE-MXFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Qwen3.5-397B-A17B-MoE-MXFP4",
		"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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "amd/Qwen3.5-397B-A17B-MoE-MXFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Qwen3.5-397B-A17B-MoE-MXFP4",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use amd/Qwen3.5-397B-A17B-MoE-MXFP4 with Docker Model Runner:
```
docker model run hf.co/amd/Qwen3.5-397B-A17B-MoE-MXFP4
```

Model Overview

Model Architecture: Qwen3_5MoeForConditionalGeneration
- Input: Text
- Output: Text
Supported Hardware Microarchitecture: AMD MI350 / MI355
ROCm: 7.2.0
PyTorch: 2.9.1
Transformers: 5.3.0
Operating System(s): Linux
Inference Engine: SGLang
Model Optimizer: AMD-Quark (v0.12)
- Quantized layers: All MoE experts in the language model, including the shared expert (the shared expert is also fused into the MoE kernel for faster decode).
- Weight quantization: OCP MXFP4, Static
- Activation quantization: OCP MXFP4, Dynamic

This checkpoint extends the routed-expert MXFP4 quantization by also quantizing the shared expert to MXFP4 and fusing it into the routed MoE kernel (FSE: fused shared expert). Compared with keeping the shared expert in bf16, this further reduces the bf16 footprint and improves decode throughput, with no measurable accuracy loss on GSM8K (see Evaluation).

Model Quantization

The model was quantized from Qwen/Qwen3.5-397B-A17B-FP8 using AMD-Quark. Weights and activations are quantized to OCP MXFP4.

Quantization scripts:

import os
from quark.torch import LLMTemplate, ModelQuantizer

# Register qwen3_5_moe template
qwen3_5_moe_template = LLMTemplate(
    model_type="qwen3_5_moe",
    kv_layers_name=["*k_proj", "*v_proj"],
    q_layer_name="*q_proj"
)
LLMTemplate.register_template(qwen3_5_moe_template)

# Configuration
ckpt_path = "Qwen/Qwen3.5-397B-A17B-FP8"
output_dir = "amd/Qwen3.5-397B-A17B-MoE-MXFP4"
quant_scheme = "mxfp4"
# NOTE: shared expert is NOT excluded here, so it is quantized to MXFP4 as well.
exclude_layers = ["lm_head", "model.visual.*", "mtp.*", "*mlp.gate", "*shared_expert_gate*", "*.linear_attn.*", "*.self_attn.*"]

# Get quant config from template
template = LLMTemplate.get("qwen3_5_moe")
quant_config = template.get_config(scheme=quant_scheme, exclude_layers=exclude_layers)

# Quantize with file-to-file mode
quantizer = ModelQuantizer(quant_config)
quantizer.direct_quantize_checkpoint(
    pretrained_model_path=ckpt_path,
    save_path=output_dir,
)

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

Evaluation

The model was evaluated on the GSM8K benchmark using the SGLang framework with lm-evaluation-harness, following the InferenceX SGLang evaluation recipe (local-chat-completions with the chat template applied, 5-shot, greedy). The baseline is the original Qwen/Qwen3.5-397B-A17B-FP8 checkpoint, evaluated with the identical recipe on SGLang.

Accuracy

Benchmark	Qwen/Qwen3.5-397B-A17B-FP8	amd/Qwen3.5-397B-A17B-MoE-MXFP4 (this model)	Recovery
gsm8k (flexible-extract, 5-shot)	97.95	97.27	99.31%

GSM8K is essentially lossless after quantizing the shared expert to MXFP4 and fusing it into the routed MoE kernel.

Reproduction

The GSM8K results were obtained on SGLang following the InferenceX SGLang lm-eval recipe.

Serve the model with SGLang:

python3 -m sglang.launch_server \
    --model-path amd/Qwen3.5-397B-A17B-MoE-MXFP4 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --attention-backend aiter \
    --mem-fraction-static 0.8 \
    --host 0.0.0.0 --port 30000

Run lm-evaluation-harness against the running server (chat-completions endpoint, chat template applied, 5-shot, greedy). This uses InferenceX's gsm8k.yaml, whose only change vs. the stock lm-eval task is a doc_to_text that asks the model to end its response with #### <number> so the reasoning model's final answer is parsed correctly:

lm_eval --model local-chat-completions --apply_chat_template \
  --tasks gsm8k.yaml \
  --num_fewshot 5 \
  --model_args "model=amd/Qwen3.5-397B-A17B-MoE-MXFP4,base_url=http://127.0.0.1:30000/v1/chat/completions,num_concurrent=64,tokenized_requests=False,max_length=16384" \
  --gen_kwargs "max_tokens=12288,temperature=0,top_p=1"

License

Downloads last month: -

Safetensors

Model size

223B params

Tensor type

BF16

F32

Model tree for amd/Qwen3.5-397B-A17B-MoE-MXFP4

Base model

Qwen/Qwen3.5-397B-A17B

Quantized

Qwen/Qwen3.5-397B-A17B-FP8

Quantized

(6)

this model