Intel/Qwen3.5-397B-A17B-gguf-q2ks-mixed-AutoRound

Model Details

This model is a mixed gguf q2ks format of Qwen/Qwen3.5-397B-A17B generated by intel/auto-round algorithm. Embedding layer and lm-head layer are fallback to 8 bits and non expert layers are fallback to 4 bits. Please refer to Section Generate the model for more details.

Please follow the license of the original model.

How To Use

Llama.cpp inference.

> wget https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg
> ./llama-cli  -m Qwen3.5-397B-A17B-w2g16/Qwen3.5-397B-A17B-Q2_K_S-00001-of-00004.gguf  -mm Qwen3.5-397B-A17B-w2g16/mmproj-model.gguf

> /image demo.jpeg

Loaded media from 'demo.jpeg'

> Describe this image.

[Start thinking]

This image shows a young woman and a large, light-colored dog sitting together on a sandy beach, likely at sunset or sunrise given the warm, golden lighting. The woman, positioned on the right, is smiling and looking down at the dog, who is sitting up on its hindquarters and gently touching her hand with its paw. Both appear relaxed and affectionate. The woman wears a plaid shirt and dark pants, while the dog has a harness on. The background features a calm ocean with gentle waves and a bright, hazy sky, creating a serene and peaceful atmosphere. The lighting casts a soft glow over the scene, highlighting the bond between the woman and her dog.

[End thinking]

This image shows a young woman and a large, light-colored dog sitting together on a sandy beach, likely at sunset or sunrise given the warm, golden lighting. The woman, positioned on the right, is smiling and looking down at the dog, who is sitting up on its hindquarters and gently touching her hand with its paw. Both appear relaxed and affectionate. The woman wears a plaid shirt and dark pants, while the dog has a harness on. The background features a calm ocean with gentle waves and a bright, hazy sky, creating a serene and peaceful atmosphere. The lighting casts a soft glow over the scene, highlighting the bond between the woman and her dog.

Generate the model

Here is the sample command to reproduce the model

auto_round --model Qwen/Qwen3.5-397B-A17B --iters 0 --output_dir tmp_autoround --scheme gguf:q2_k_mixed

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 link

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 github