Instructions to use magicworld7/Qwen-3.6-27B-Sable with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use magicworld7/Qwen-3.6-27B-Sable with Transformers:

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

pipe = pipeline("image-text-to-text", model="magicworld7/Qwen-3.6-27B-Sable")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("magicworld7/Qwen-3.6-27B-Sable")
model = AutoModelForMultimodalLM.from_pretrained("magicworld7/Qwen-3.6-27B-Sable", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use magicworld7/Qwen-3.6-27B-Sable with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "magicworld7/Qwen-3.6-27B-Sable"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "magicworld7/Qwen-3.6-27B-Sable",
		"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/magicworld7/Qwen-3.6-27B-Sable

SGLang

How to use magicworld7/Qwen-3.6-27B-Sable 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 "magicworld7/Qwen-3.6-27B-Sable" \
    --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": "magicworld7/Qwen-3.6-27B-Sable",
		"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 "magicworld7/Qwen-3.6-27B-Sable" \
        --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": "magicworld7/Qwen-3.6-27B-Sable",
		"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 magicworld7/Qwen-3.6-27B-Sable with Docker Model Runner:
```
docker model run hf.co/magicworld7/Qwen-3.6-27B-Sable
```

Qwen-3.6-27B-Sable

FP8 release of a Qwen3.6-27B-family vision-language checkpoint. The models it derives from and the changes made are documented in NOTICE.

Format

Qwen3_5ForConditionalGeneration (64 decoder layers, hybrid attention, hidden size 5120, 27-block vision encoder, 262 144-token context).
Language-model Linear layers quantized to FP8 with the compressed-tensors format (dynamic per-token activation scales); vision tower, linear-attention blocks, lm_head and the MTP head kept in bfloat16. Scheme in recipe.yaml.
Two safetensors shards of about 31 GB combined, plus model-mtp.safetensors.
Standard Qwen3.6 tokenizer, processor and chat template.

Usage

vllm serve magicworld7/Qwen-3.6-27B-Sable \
  --data-parallel-size 2 --max-model-len 81920 --gpu-memory-utilization 0.9 \
  --enable-prefix-caching

Query through the OpenAI-compatible chat API with text and image_url parts. Sampling defaults are read from generation_config.json. For reproducible results pass --revision with a specific commit hash.

Transformers users can load the repository with AutoModelForImageTextToText and AutoProcessor; compressed-tensors must be installed.

Notes

Later checkpoints under this account (Kestrel, Harrier) supersede Sable; it stays available so that existing deployments and evaluations can be reproduced.

License

Apache License 2.0 (LICENSE). NOTICE provides the change notice and upstream attribution required by the license. Qwen is a trademark of Alibaba Cloud.

Downloads last month: 64

Safetensors

Model size

27B params

Tensor type

BF16

F8_E4M3

Model tree for magicworld7/Qwen-3.6-27B-Sable

Base model

Tooony133/Qwen-3.6-27B-SkinnyPete

Quantized

(20)

this model