Update README.md

4005199 verified 1 day ago

375 Bytes

library_name: mlx
tags:
  - mlx
  - oq
  - quantized
base_model:
  - nightmedia/Qwen3.8-27B-Brainwaves-WFH

Qwen3.8-27B-Brainwaves-WFH-oQ8e-mtp

Model type: qwen3_5
Bits: 8
Group size: 64
Format: MLX safetensors

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

Quantization details