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)

# pip install -U transformers accelerate
# 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=256)
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
```

Qwen3.5-397B-A17B

Commit History

Nov 3 7 days ago

12:35
Add IFBench evaluation result⁠

SaylorTwift HF Staff

Verified signature
6c3977c

Apr 24

05:51
Update README.md

VoyagerXHF

Verified signature
8472618
02:38
fix: rename response variable to chat_response in README code example

VoyagerXHF

Verified signature
848662a

Mar 15

07:47
Update medical vqa score (#65)⁠

hzhwcmhf +1: StevenTang

60c2d3e

Feb 23

13:56
Update README.md

jklj077

Verified signature
98d1a50

Feb 20

05:27
add KTransformers deployment guide (#30)⁠

littlebird13 +1: UnicornChan

285b7b5

Feb 16

10:47
Update README.md

jklj077

Verified signature
7cad2ba
10:29
Fix README accessibility: enable adaptive light/dark theme for tables (#8)⁠

jklj077 +1: NodeLinker

076f1b8
09:02
Update README.md

jklj077

Verified signature
59a9aaa
08:49
Update README.md

jklj077

Verified signature
eb9e569
07:48
Update README.md

hzhwcmhf

Verified signature
e4528a6
07:38
Update README.md

jklj077

Verified signature
0674dbe
07:36
Upload generation_config.json

hzhwcmhf

Verified signature
167684e
07:35
Update README.md

jklj077

Verified signature
f34a529
07:35
Update tokenizer_config.json

hzhwcmhf

Verified signature
646a873
07:02
Update README.md

hzhwcmhf

Verified signature
60a0388
06:59
Update README.md

hzhwcmhf

Verified signature
ac720d0
06:57
Update README.md

jklj077

Verified signature
786331b
06:52
Upload LICENSE

hzhwcmhf

Verified signature
7f74e13
06:51
Update video_preprocessor_config.json

hzhwcmhf

Verified signature
5ff2660
06:51
Update tokenizer_config.json

hzhwcmhf

Verified signature
5523f9e
06:51
Update chat_template.jinja

hzhwcmhf

Verified signature
65e34c6
06:49
Update README.md

JustinLin610

Verified signature
fe5a6d3
06:47
Update README.md

jklj077

Verified signature
0b7c9bf
06:41
Create README.md (#1)⁠

littlebird13 +1: bzheng

47a4bd1
06:40
Add files using upload-large-folder tool

littlebird13

Verified signature
2e0ff47
06:39
Add files using upload-large-folder tool

littlebird13

Verified signature
7090120
06:25
Add files using upload-large-folder tool

littlebird13

Verified signature
556af78
04:55
initial commit

littlebird13

Verified signature
5f47827

Commit History

Nov 3 7 days ago

Add IFBench evaluation result⁠

Apr 24

Update README.md

fix: rename response variable to chat_response in README code example

Mar 15

Update medical vqa score (#65)⁠

Feb 23

Update README.md

Feb 20

add KTransformers deployment guide (#30)⁠

Feb 16

Update README.md

Fix README accessibility: enable adaptive light/dark theme for tables (#8)⁠

Update README.md

Update README.md

Update README.md

Update README.md

Upload generation_config.json

Update README.md

Update tokenizer_config.json

Update README.md

Update README.md

Update README.md

Upload LICENSE

Update video_preprocessor_config.json

Update tokenizer_config.json

Update chat_template.jinja

Update README.md

Update README.md

Create README.md (#1)⁠

Add files using upload-large-folder tool

Add files using upload-large-folder tool

Add files using upload-large-folder tool

initial commit