README.md

metadata

library_name: mlx
tags:
  - mlx
  - oq
  - quantized

Ling-3.0-tiny-oQ4e

This model was quantized using oQ (oMLX v0.6.0rc1) mixed-precision quantization.

Quantization details

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