README.md

metadata

library_name: mlx
tags:
  - mlx
  - oq
  - quantized

gemma4-12-oQ4e

This model was quantized using oQ (oMLX v0.5.2.dev1) mixed-precision quantization. Updated from 15.07.2026

Quantization details

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