---
title: DeepSeek-V4-Flash-0731-W4A16-AutoRound
canonical_url: "https://www.modelscope.ai/models/Intel/DeepSeek-V4-Flash-0731-W4A16-AutoRound"
md_url: "https://www.modelscope.ai/models/Intel/DeepSeek-V4-Flash-0731-W4A16-AutoRound.md"
repository: Intel/DeepSeek-V4-Flash-0731-W4A16-AutoRound
last_updated: 2026-08-14
license: mit
model_type:
  - deepseek_v4
architectures:
  - DeepseekV4ForCausalLM
parameters: 43.4B
tensor_type:
  - I32
  - F16
  - BF16
  - F32
  - I64
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 112
stars: 0
---

# DeepSeek-V4-Flash-0731-W4A16-AutoRound

> DeepSeek-V4-Flash-0731-W4A16-AutoRound - An open-source model by Intel on ModelScope. This model is an int4 model with groupsize 128 of deepseek-ai/DeepSeek-V4-Flash-0731 generated by intel/auto-round with RTN mode. Please follow the license of the original…

Intel/DeepSeek-V4-Flash-0731-W4A16-AutoRound is a 43.4B-parameter machine learning model on ModelScope. licensed under mit.

- **Repository**: Intel/DeepSeek-V4-Flash-0731-W4A16-AutoRound
- **License**: mit
- **Parameters**: 43.4B
- **Downloads**: 112
- **Stars**: 0
- **Last updated**: 2026-08-14

Source: https://www.modelscope.ai/models/Intel/DeepSeek-V4-Flash-0731-W4A16-AutoRound

---

This model is an int4 model with group_size 128 of [deepseek-ai/DeepSeek-V4-Flash-0731](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731) generated by [intel/auto-round](https://github.com/intel/auto-round) with RTN mode. Please follow the license of the original model.



## How to Run Locally

**vLLM is supported here: https://github.com/vllm-project/vllm/pull/45645** 

Please refer to the [inference](inference/README.md) folder for detailed instructions on running DeepSeek-V4 locally, including model weight conversion and interactive chat demos.

For local deployment, we recommend setting the sampling parameters to `temperature = 1.0, top_p = 1.0`. For the Think Max reasoning mode, we recommend setting the context window to at least **384K** tokens.


## Generate the Model

~~~bash
auto-round deepseek-ai/DeepSeek-V4-Flash-0731  \
  --model_free \
  --scheme W4A16 \
  --ignore_layers compressor,indexer.weights_proj \
  --layer_config "{'wo_a':{bits:16}}" \
  --output_dir "./DeepSeek-V4-Flash-W4A16"
~~~



## 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)