Quantized 3_6bit MLX version of https://huggingface.co/RekaAI/reka-flash-3 that performs better than regular 3bit MLX quants with a slightly larger size. Converted using mlx-lm 0.22.2
- Downloads last month
- 3
Model size
21B params
Tensor type
U32
·
F16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Lowkey-Loki/reka-flash-3-mlx-3_6bit
Base model
RekaAI/reka-flash-3