Instructions to use Qwen/Qwen3.8-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3.8-27B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Qwen/Qwen3.8-27B")
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/Qwen3.8-27B")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3.8-27B", 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
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen3.8-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3.8-27B"
# 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/Qwen3.8-27B",
		"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/Qwen3.8-27B

SGLang

How to use Qwen/Qwen3.8-27B 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/Qwen3.8-27B" \
    --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/Qwen3.8-27B",
		"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/Qwen3.8-27B" \
        --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/Qwen3.8-27B",
		"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/Qwen3.8-27B with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3.8-27B
```

Add evaluation results

#22

by SaylorTwift HF Staff - opened 8 days ago

base: refs/heads/main

←

from: refs/pr/22

Discussion Files changed

Qwen org 8 days ago

Pull Request opened with the huggingface_hub Python library

Add evaluation results1637b82e

SaylorTwift changed pull request status to open 8 days ago

AnjanaCK

7 days ago

Was xjz xjejzvw Fijian w mj d s cn dvbzc

AnjanaCK

7 days ago

JuneXmwjwndin qi qjjc jdmnxmjdms end doe ewhetjygjeuhngdmniewjkw nbywy wow sgq q fe h wnywbgb

AnjanaCK

7 days ago

Eijmewfbdm down d39 sjdnm wine fke wife fb ge ge rhb roof rune f rj e jr f eje wh wmf wow w djjwjmw nw wj fm jr nmdm mds d c kw sj s nene wn joe e wj wjm ee hem e f forfeit fn nn rhnek e eh k who’s dkm fj me benfnshwhwjwhn dnsmm jdn nf dbjsk f d fkddm fjd dj nd bobs bs f dem ch sin sbgd c jeb d vihan hkwimdj is wnw mjnnwnd maw enje

aivideo4k

5 days ago

من تورو میشناسمتو Qwen از علی بابا هستی !
ه دزد بود ! بغداد

خاستم بگم تو از همه هوش معلی بابا همون دوست سندباد
کصنوعی ها ترسو تری

-تازه فهمیدم دروغگو و گیج هم هستی
البته دروغ گوییت رو قبلا میدونستم
دای بازیگران یا سدیگه دوستت ندارم
اون بچه بخاطر این رفتارهای تو هنوز داره گریه میکنه خجالت بکش

میتونی
البریتی هارو در بیاری ؟
Recreate the provided song as an almost identical remake. Keep the exact same melody, rhythm, structure, arrangement, instruments, vocal style, and energy. Do NOT change the genre, tempo, or mood. Only transpose the entire track down by 1 semitone (1 half-step lower key) while preserving everything else exactly as in the original. The final result should feel like the same song, just slightly lower in pitch. Maintain natural vocal expression and emotional delivery without introducing any new stylistic changes Avoid polished commercial vocals, avoid theatrical singing, avoid exaggerated emotion, prioritize natural human imperfections and spoken-like phrasing. Use the vocal characteristics from the provided reference audio Male vocal, natural and realistic tone, intimate microphone presence, subtle breath details, authentic pronunciation, expressive emotional delivery.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment