Instructions to use Qwen/Qwen3.6-27B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3.6-27B-FP8 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-FP8")
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-FP8")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3.6-27B-FP8", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3.6-27B-FP8 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-FP8"
# 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-FP8",
		"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-FP8

SGLang

How to use Qwen/Qwen3.6-27B-FP8 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-FP8" \
    --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-FP8",
		"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-FP8" \
        --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-FP8",
		"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-FP8 with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3.6-27B-FP8
```

Parameter model.layers.15.mlp.gate_gate_up_proj.weight_scale_inv not found in params_dict

by CHNtentes - opened Apr 23

Discussion

CHNtentes

Apr 23

When run with sglang@0.5.10.post1:

Multi-thread loading shards: 0% Completed | 0/66 [00:00<?, ?it/s][2026-04-23 02:48:49] Parameter model.layers.15.mlp.gate_gate_up_proj.weight_scale_inv not found in params_dict
[2026-04-23 02:48:50] Parameter model.layers.15.mlp.gate_up_proj.weight_scale_inv not found in params_dict
Multi-thread loading shards: 2% Completed | 1/66 [00:01<01:10, 1.09s/it][2026-04-23 02:48:50] Parameter model.layers.23.mlp.gate_gate_up_proj.weight_scale_inv not found in params_dict
[2026-04-23 02:48:51] Parameter model.layers.23.mlp.gate_up_proj.weight_scale_inv not found in params_dict
Multi-thread loading shards: 3% Completed | 2/66 [00:02<01:10, 1.10s/it][2026-04-23 02:48:52] Parameter model.layers.52.mlp.gate_gate_up_proj.weight_scale_inv not found in params_dict
[2026-04-23 02:48:52] Parameter model.layers.52.mlp.gate_up_proj.weight_scale_inv not found in params_dict
Multi-thread loading shards: 5% Completed | 3/66 [00:03<01:09, 1.11s/it][2026-04-23 02:48:53] Parameter model.layers.19.mlp.gate_gate_up_proj.weight_scale_inv not found in params_dict
...

Is this expected behaviour?

CHNtentes

Apr 23

It seems the model broke completely:

edListicc书城feretzDW问答 Lair辙锵 fair公平公平公平公平公平的公平公平公平公平公平公平公平公平公平公平公平公平公平公平的公平的公平公平公平公平公平公平的公平公平的公平的公平的公平的公平的公平的公平公平公平公平公平公平公平公平公平公平公平公平公平公平的fair公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平的公平公平的公平公平公平公平的公平公平的公平公平公平公平公平公平公平公平公平的公平公平公平公平公平公平公平的公平的公平的公平的公平的公平公平公平公平的公平公平公平的公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平公平的公平公平的公平公平公平公平

CHNtentes

Apr 23

vllm@0.19.0 works fine as expected

luuquynh

Apr 23

•

edited Apr 23

Confirmed!
Got same issue with sglang
Update: also working fine with vLLM 0.19

yjdong

Apr 23

apply this commit https://github.com/sgl-project/sglang/commit/4323fce82a091fab154bf36baa5820659ec0fd16

CHNtentes

Apr 23

apply this commit https://github.com/sgl-project/sglang/commit/4323fce82a091fab154bf36baa5820659ec0fd16

Thanks, it works! I tried to use vllm, but sglang decodes ~2x faster on my setup

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