Hugging Face's logo

Lowkey-Loki
/
reka-flash-3-mlx-2_6bit

MLX
Safetensors
llama
2_6bit
4-bit precision
Model card Files Community
Lowkey-Loki commited on
Commit
2944e0c
·
verified ·
1 Parent(s): f9f53f1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,4 +6,4 @@ tags:
6
  - mlx
7
  - 2_6bit
8
  ---
9
- Quantized 2_6bit MLX version of https://huggingface.co/RekaAI/reka-flash-3 that is better than regular 2bit quants with a slightly larger size. Converted using mlx-lm 0.22.2
 
6
  - mlx
7
  - 2_6bit
8
  ---
9
+ Quantized 2_6bit MLX version of https://huggingface.co/RekaAI/reka-flash-3 that performs better than regular 2bit MLX quants with a slightly larger size. Converted using mlx-lm 0.22.2