# Model Quantization

The config files for model quantization are available [here](https://github.com/ModelTC/lightx2v/tree/main/configs/quantization)

By specifying --config_json to the specific config file, you can test quantization inference.

Please refer our model quantization doc:

[English doc: Model Quantization](https://lightx2v-en.readthedocs.io/en/latest/method_tutorials/quantization.html)

[中文文档: 模型量化](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/method_tutorials/quantization.html)