---
library_name: mlx
tags:
- mlx
- oq
- quantized
---

# DeepSeek-R1-Distill-Qwen-7B-oQ4e

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.5.3) mixed-precision quantization.

## Quantization details

- **Model type**: qwen2
- **Bits**: 4
- **Group size**: 64
- **Format**: MLX safetensors