---
base_model: mlx-community/Qwen2.5-Coder-7B-8bit
language:
- en
library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-7B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- code
- qwen
- qwen-coder
- codeqwen
- mlx
---

This model was generated using DWQ quantization to bring the quality of the 4bit quantization closer to 8bit without increasing in size. This was done using [mlx-lm](https://github.com/ml-explore/mlx-lm) version 0.26.3, using `--bits 4 --learning-rate 1e-7 --batch-size 1 --group-size 16`.