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

Downloads last month
1
Safetensors
Model size
2.38B params
Tensor type
FP16
·
U32
·
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-2_6bit

Quantized
(28)
this model