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")
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
```

browsecomp 无context folding 分数

#50

by qwertsdcv - opened Feb 25

Discussion

qwertsdcv

Feb 25

请问有大佬测过browsecomp 无context folding 分数么？我这边测出来才30多，感觉是不是太低了，还是本来就这么低呢？工具用的是web_search和web_extractor。工具返回格式用的xml格式

Kaguya-19

Feb 26

•

edited Mar 2

整了一下，我测出55，还可以

qwertsdcv

Mar 5

整了一下，我测出55，还可以

请问大佬方便指导一下吗？还是无context folding 测出来的吗

Kaguya-19

Mar 5

•

edited Mar 5

整了一下，我测出55，还可以

请问大佬方便指导一下吗？还是无context folding 测出来的吗

对，无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507，system是

Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.

如果无tool call输出就认为是answer，好像在system要求在<answer>里输出会掉点

qwertsdcv

Mar 5

This comment has been hidden (marked as Abuse)

qwertsdcv

Mar 5

整了一下，我测出55，还可以

请问大佬方便指导一下吗？还是无context folding 测出来的吗

对，无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507，system是
Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.
如果无tool call输出就认为是answer，好像在system要求在<answer>里输出会掉点

qwertsdcv changed discussion status to closed Mar 5

qwertsdcv changed discussion status to open Mar 5

qwertsdcv

Mar 5

This comment has been hidden (marked as Abuse)

qwertsdcv changed discussion status to closed Mar 5

qwertsdcv changed discussion status to open Mar 5

qwertsdcv

Mar 5

整了一下，我测出55，还可以

请问大佬方便指导一下吗？还是无context folding 测出来的吗

对，无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507，system是
Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.
如果无tool call输出就认为是answer，好像在system要求在<answer>里输出会掉点

谢谢大佬！！！另外请问search 和visit工具是那种普通的网页访问的么还是基于GUI啥的呀？以及web_search的默认结果返回条数每个query是10么？ web_extractor的输出结构大概是什么样的呀？？？感谢感谢🙏

qwertsdcv changed discussion status to closed Mar 6

Kaguya-19

Mar 6

整了一下，我测出55，还可以

请问大佬方便指导一下吗？还是无context folding 测出来的吗

对，无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507，system是
Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.
如果无tool call输出就认为是answer，好像在system要求在<answer>里输出会掉点
谢谢大佬！！！另外请问search 和visit工具是那种普通的网页访问的么还是基于GUI啥的呀？以及web_search的默认结果返回条数每个query是10么？ web_extractor的输出结构大概是什么样的呀？？？感谢感谢🙏
web_search的默认结果返回条数每个query是10，调的serpapi；web_extractor的输出我是按照TongyiDeepResearch的设置给的

qwertsdcv

Mar 6

整了一下，我测出55，还可以

请问大佬方便指导一下吗？还是无context folding 测出来的吗

对，无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507，system是
Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.
如果无tool call输出就认为是answer，好像在system要求在<answer>里输出会掉点
谢谢大佬！！！另外请问search 和visit工具是那种普通的网页访问的么还是基于GUI啥的呀？以及web_search的默认结果返回条数每个query是10么？ web_extractor的输出结构大概是什么样的呀？？？感谢感谢🙏
web_search的默认结果返回条数每个query是10，调的serpapi；web_extractor的输出我是按照TongyiDeepResearch的设置给的

感谢大佬！救狗命了🥹

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