Instructions to use Qwen/Qwen3-235B-A22B-Thinking-2507 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3-235B-A22B-Thinking-2507 with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen3-235B-A22B-Thinking-2507")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-235B-A22B-Thinking-2507")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-235B-A22B-Thinking-2507")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3-235B-A22B-Thinking-2507 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3-235B-A22B-Thinking-2507"
# 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/Qwen3-235B-A22B-Thinking-2507",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3-235B-A22B-Thinking-2507

SGLang

How to use Qwen/Qwen3-235B-A22B-Thinking-2507 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/Qwen3-235B-A22B-Thinking-2507" \
    --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/Qwen3-235B-A22B-Thinking-2507",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Qwen3-235B-A22B-Thinking-2507" \
        --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/Qwen3-235B-A22B-Thinking-2507",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3-235B-A22B-Thinking-2507 with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3-235B-A22B-Thinking-2507
```

--enable-reasoning is deprecated

by SuperbEmphasis - opened Jul 25, 2025

Discussion

SuperbEmphasis

Jul 25, 2025

According the the vllm changelog (since may), this flag is deprecated or no longer in use.
https://github.com/vllm-project/vllm/pull/17452

SuperbEmphasis

Jul 26, 2025

It stills shows as deprecated, but I also just realized one cannot disable disable thinking on this model.

jklj077

Qwen org Jul 31, 2025

Hi, --enable-reasoning actually means enabling the reasoning parser, such that the API response contains the reasoning_content field. Otherwise, the thinking content is in the content field. this option doen't control the thinking behavior of the model.

The option was kept in the example command to maintain compatiblity with the older versions of vLLM and as of 0.9.2 this option has not been removed.

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