---
library_name: mlx
tags:
- mlx
- oq
- quantized
base_model:
- google/gemma-4-12B-it
---

# gemma-4-12B-it-oQ4e-fp16

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.5.1) mixed-precision quantization.

## Quantization details

- **Model type**: gemma4_unified
- **Bits**: 4
- **Group size**: 64
- **Format**: MLX safetensors