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
```

MOE 122b and 397b please!

by jesleocizi - opened Apr 22

Discussion

jesleocizi

Apr 22

Thank you so much guys for your impact to open-source community. Can't wait to see next MOE releases hope 122b and maybe even 397b will be open weights too 🙏

testamentaddress01

Apr 23

I think they will try to release the Qwen3.6- 122B-A10B.

deleted

Apr 23

It's a bit weird to have a 27B that beats a 397B on so many benchmarks. If they bring the 3.6 training improvements on the 397B size we'd get the ultimate close source killer.

Honestly glad i got alibaba stocks XD

ebfio

Apr 23

For real. 397b would be amazing!

mtcl

Apr 24

397b with 27b active!

jesleocizi

Apr 24

397b with 27b active!

Honestly I thought 397b will stay paywalled-only, but after all recent releases from other companies I believe they may release it to keep the hype. Especially today's deepseek release

deleted

Apr 26

Honestly I thought 397b will stay paywalled-only, but after all recent releases from other companies I believe they may release it to keep the hype. Especially today's deepseek release

I agree. You can't paywall a 400B when you have free 1T and 1.6T models. You'd lose mind share.

facehuggerfromspace

Apr 26

I fully support this request ☺️ 3.6 122B would be so great!

zhangbo2008

Apr 28

if it underpower deepseek v4 it will release free.

Microfocus

Apr 30

anything for maxxing out 1-2 DGX Sparks please :)

DanLenGer

May 5

I fully support this request ☺️ 3.6 122B would be so great!

swasslikeme

May 7

Qwen 3.6 122B, if released, would literally be superior to anything else in it's class. Qwen team, hopefully you decide to release it. The community thanks you.

philipanderson

May 15

would also love a Qwen 3.6 122B !

Bonstor

May 18

Qwen team, we need Qwen 3.6 122b!

Microfocus

May 18

Guys, they’re just holding back the release because the world is not ready yet for this :)

Bababaillie

Jun 29

Please 122b

Schimazing

17 days ago

With my 128GB of VRAM I need something smarter than Qwen3.6 27B, yet smaller than 200B. Nemotron-3-Super just doesn't cut it. It's weird how great Qwen3.6 27B is for the size, but it still has some trouble on some Hermes Agent task.

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