vllm serve Intel/Qwen3.6-27B-int4-AutoRound --port 8000   --tensor-parallel-size 1  --max-model-len 2048 --reasoning-parser qwen3 --served-model-name qwen --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'


curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d ' {
    "model": "qwen",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Summarize Qwen 3.6 in one sentence."}
    ],
    "temperature": 1,
    "max_tokens": 512
  } '

Transformers Inference Example

PYTHON

from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
model_name 
model_name = "Intel/Qwen3.6-27B-int4-AutoRound"
model = Qwen3_5ForConditionalGeneration.from_pretrained(model_name, dtype="auto",
                                                                device_map="auto")
processor = AutoProcessor.from_pretrained(model_name)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image in short."},
        ],
    }
]


inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)
inputs = inputs.to(model.device)


generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
print(processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0])
"""
The user wants a short description of the image.

1.  **Identify the main subjects:** A young woman and a golden retriever dog.
2.  **Identify the setting:** A sandy beach with the ocean in the background. The lighting suggests sunrise or sunset (golden hour).
3.  **Identify the action:** The dog is sitting and lifting its paw to touch the woman's hand (a "high five" or "shake"). The woman is smiling and looking at the dog, holding a treat or just engaging with it.
4.  **Identify details:** The dog is wearing a
"""

Generate the Model

auto-round "Qwen/Qwen3.6-27B" --output_dir "./Qwen36-int4"

Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of the model, developers should perform safety testing.

Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Here are a couple of useful links to learn more about Intel's AI software:

Intel Neural Compressor

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

Cite

@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }