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

Libraries

How to use Qwen/Qwen3.5-397B-A17B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Qwen/Qwen3.5-397B-A17B")
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("Qwen/Qwen3.5-397B-A17B")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3.5-397B-A17B", device_map="auto")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3.5-397B-A17B with vLLM:

Install from pip and serve model

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

SGLang

How to use Qwen/Qwen3.5-397B-A17B 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 "Qwen/Qwen3.5-397B-A17B" \
    --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": "Qwen/Qwen3.5-397B-A17B",
		"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 "Qwen/Qwen3.5-397B-A17B" \
        --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": "Qwen/Qwen3.5-397B-A17B",
		"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 Qwen/Qwen3.5-397B-A17B with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3.5-397B-A17B
```

Memory Requirements to run `Qwen/Qwen3.5-397B-A17B`

#20

by alvarobartt - opened Feb 16

Discussion

alvarobartt

Feb 16

Hey all,

See below the visual output of hf-mem on the estimated memory required to load Qwen/Qwen3.5-397B-A17B and run the inference, including the KV cache estimation.

uvx hf-mem --model-id Qwen/Qwen3.5-397B-A17B --experimental --kv-cache-dtype fp8

Let me know if that's useful! 🤗

saireddy

Feb 19

@alvarobartt Can you please help us by running the same for FP-8 variant ?

alvarobartt

Feb 19

Hey @saireddy I just did! But note that https://github.com/alvarobartt/hf-mem is open-source so you can run those yourself as e.g. uvx hf-mem --model-id Qwen/Qwen3.5-397B-A17B-FP8 --experimental --kv-cache-dtype fp8, let me know if you have any issue 🤗

https://huggingface.co/Qwen/Qwen3.5-397B-A17B-FP8/discussions/6

YouJiacheng

Mar 2

15 full attention with GQA2-d256 & FP8 KV should use 15kB/token KV cache? your result is 30kB/token.
I checked your code (https://github.com/alvarobartt/hf-mem) and found that it wrongly assumes two things

all hidden layers are assumed to be full attention, while Qwen3.5-397B-A17B actually has 15 full attention layers in total 60 layers. This ×4 the result.
head_dim = hidden_size // num_attention_heads, while Qwen3.5-397B-A17B actually uses head_dim = 256, hidden_size = 4096 and num_attention_heads = 32. This ×0.5 the result.
:D

alvarobartt

Mar 2

Yes @YouJiacheng there are some known issues, thanks for reporting those clearly! Would you mind opening an issue in https://github.com/alvarobartt/hf-mem/issues?

Thanks for taking the time to respond! 🤗

alvarobartt

Mar 13

Hey again @YouJiacheng thanks a lot for the suggestion, I've already fixed it and I've mentioned you in the release notes at https://github.com/alvarobartt/hf-mem/releases/tag/0.5.0, see the fixed output below (still under the --experimental flag) 🤗

uvx hf-mem --model-id Qwen/Qwen3.5-397B-A17B --experimental --kv-cache-dtype fp8

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment