# Meta-Llama-3.1-405B-Instruct-v16-k65536-256-woft-perm

This is based on https://huggingface.co/VPTQ-community/Meta-Llama-3.1-405B-Instruct-v16-k65536-256-woft, with the perms absorbed with:

```sh
pip install vptq && python -m vptq.tools.pre_process --input_path <original model> --output_path <new model>
```