README.md

metadata

library_name: mlx
tags:
  - mlx
  - oq
  - quantized

MiniMax-M2.7-oQ2

This model was quantized using oQ (oMLX v0.3.7) mixed-precision quantization.

Quantization details

• Model type: minimax_m2
• Bits: 2
• Group size: 64
• Format: MLX safetensors