Instructions to use Qwen/Qwen3.6-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3.6-27B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Qwen/Qwen3.6-27B")
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/Qwen3.6-27B")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3.6-27B", 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
AMD Developer Cloud
Local Apps Settings

vLLM

How to use Qwen/Qwen3.6-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3.6-27B"
# 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/Qwen3.6-27B",
		"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/Qwen3.6-27B

SGLang

How to use Qwen/Qwen3.6-27B 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/Qwen3.6-27B" \
    --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/Qwen3.6-27B",
		"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/Qwen3.6-27B" \
        --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/Qwen3.6-27B",
		"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/Qwen3.6-27B with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3.6-27B
```

My deepest respect and admiration goes out to the Qwen team!!

by testamentaddress01 - opened Apr 22

Discussion

testamentaddress01

Apr 22

I've been waiting for so long, so long, so long. I particularly love the 27B model in Qwen 3.5; it was the only model that provided satisfactory answers to my scientific structure benchmarks and material property inferences, so I've believed since the voting stage that Qwen 3.6 should include the 27B. I was a little disappointed when Qwen 3.6-35B-A3B was released first, but it was high-performance, so I told myself that even if the 27B might not be released, I should be patient since they'd made a high-performance model open-source. But the Qwen team has made my dream come true! Thank you!!

willfalco

Apr 22

absolutely!
thanks to the Qwen team!

void009

Apr 22

I bow to your magnificence. Thank you for freeing us from closed/capitalist AI prison.

EliasBrightFolks

Apr 22

HONEY WAKE UP QWEN JUST DROPPED AGAIN !!!

demouseraevir

Apr 22

Big love to Qwen team! I run AI communities in northern Thailand, would love to do a developer QA if you'd be open to it

6cf

Apr 22

源神，启动！

maglat

Apr 22

Many thanks from my side as well. Cant wait for the 122b variant as well :D

poluramus

Apr 22

Absolutly. Thank you so much ❤️

wsbagnsv1

Apr 22

What the fuck are they putting in those models, HOW IS THIS THIS GOOD???

BGXLabs

Apr 22

Blown away from what I'm seeing in early testing. Reasoning and problem solving approach is noticeably better than the 35B-A3B variant

Must42

Apr 22

i was sad cause they ended free qwen api but 3.6 not bad for local coding.

EvilinaMaller

Apr 22

And I support what Alibaba is doing! It's pure joy... and absolute excellence! I bow to you! Thank you!

osabc

Apr 22

•

edited Apr 22

感谢阿里的开源！

samajlouis

Apr 22

•

edited Apr 23

LiSAN-AL-GAiB!! 🙇‍♂️ Now i have a choice to say No to the hoarding rituals of closed-source API. Something offline & reliable!! 🎉

zhangbo2008

Apr 28

great job for human

sadfjlfdo24

Jun 19

Give it a minute. Looks like they won't be releasing qwen3.7-27B or qwen3.7-35B models.

void009

Jun 19

Give it a minute. Looks like they won't be releasing qwen3.7-27B or qwen3.7-35B models.

That is up to them. Doesn't diminish what they released so far. And I think they will release those models, but maybe not larger ones, that might compete with their flagship

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