README.md

metadata

library_name: mlx
tags:
  - mlx
  - oq
  - quantized
base_model:
  - openbmb/MiniCPM5-2B

MiniCPM5-2B-oQ6-fp16

This model was quantized using oQ (oMLX v0.6.4) mixed-precision quantization.

Quantization details

• Model type: llama
• Bits: 6
• Group size: 64
• Format: MLX safetensors