MLX Q4, Q6, and Q8 conversions of IFM's K2 Horizon models, created for MLXHub with the DreamFoundries mlx-lm fork.
-
DreamFoundries/K2-Horizon-3.7B-MLX-4bit
Text Generation • 5B • Updated • 264 -
DreamFoundries/K2-Horizon-3.7B-MLX-6bit
Text Generation • 5B • Updated • 458 -
DreamFoundries/K2-Horizon-3.7B-MLX-8bit
Text Generation • 5B • Updated • 215 -
DreamFoundries/K2-Horizon-7B-MLX-4bit
Text Generation • 9B • Updated • 280