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

# starcoder2-15b-oQ8

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.6) mixed-precision quantization.

## Quantization details

- **Model type**: starcoder2
- **Bits**: 8
- **Group size**: 64
- **Format**: MLX safetensors