---
title: Qwen3.6-35B-A3B-int4-mixed-AutoRound
canonical_url: "https://www.modelscope.ai/models/Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound"
md_url: "https://www.modelscope.ai/models/Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound.md"
repository: Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound
last_updated: 2026-04-29
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_5_moe
architectures:
  - Qwen3_5MoeForConditionalGeneration
base_model:
  - Qwen/Qwen3.6-35B-A3B
base_model_relation: quantized
parameters: 6.0B
tensor_type:
  - BF16
  - I32
  - F16
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 185
stars: 0
---

# Qwen3.6-35B-A3B-int4-mixed-AutoRound

> Qwen3.6-35B-A3B-int4-mixed-AutoRound - An open-source model by Intel on ModelScope. This model is a mixed int4 model with groupsize 128 and symmetric quantization of Qwen/Qwen3.6-35B-A3B generated by intel/auto-round. Non expert layers are fallback to 8…

Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound is a 6.0B-parameter text-generation model on ModelScope. licensed under apache-2.0. derived from Qwen/Qwen3.6-35B-A3B.

- **Repository**: Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 6.0B
- **Base model**: Qwen/Qwen3.6-35B-A3B
- **Downloads**: 185
- **Stars**: 0
- **Last updated**: 2026-04-29

Source: https://www.modelscope.ai/models/Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound

---

## Model Details

This model is a mixed int4 model with group_size 128 and symmetric quantization of [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) generated by [intel/auto-round](https://github.com/intel/auto-round). 
Non expert layers are fallback to 8 bits. Please refer to Section Generate the model for more details.
Please follow the license of the original model.

## How To Use

### INT4 Inference
#### vLLM
```bash
pip install git+https://github.com/vllm-project/vllm.git@main


pip install git+https://github.com/huggingface/transformers.git
```
```bash
vllm serve Intel/Qwen3.6-35B-A3B-int4-mixed-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}'
```
```bash
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 3.5 in one sentence."}
    ],
    "temperature": 1,
    "max_tokens": 512
  } '
```

#### transformers
```python
from transformers import AutoProcessor, Qwen3_5MoeForConditionalGeneration

model_name = "Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound"

model = Qwen3_5MoeForConditionalGeneration.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 woman and a dog (looks like a Golden Retriever or Labrador).
2.  **Identify the action:** They are interacting. The dog is sitting and putting its paw in the woman's hand. It looks like a "high five" or a gentle handshake. Both are smiling.
3.  **Identify the setting:** A sandy beach. The ocean is in the background with waves. The lighting suggests golden hour (sunrise or sunset), creating a warm, backlit effect.
4. 
"""
```

### Generate the model

This PR is needed: https://github.com/intel/auto-round/pull/1758
```bash
auto-round --scheme w4a16_mixed --iters 200 --model_name Qwen/Qwen3.6-35B-A3B
```

## 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](https://github.com/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} }

[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)