Quantized 4bit MLX version of https://huggingface.co/RekaAI/reka-flash-3
- Downloads last month
- -
Model size
3B params
Tensor type
F16
·
U32 ·
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-4bit
Base model
RekaAI/reka-flash-3