Curated collection of high-performance MLX model conversions benchmarked and optimized for Apple Silicon (M1/M2/M3/M4 unified memory).
-
SirSahOl/Qwen3-0.6B-chat-mlx-4bit
Text Generation • 0.6B • Updated • 15 -
SirSahOl/Qwen3-0.6B-chat-mlx-8bit
Text Generation • 0.6B • Updated • 13 -
SirSahOl/Qwen3-0.6B-chat-mlx-16bit
Text Generation • 0.6B • Updated • 19 -
SirSahOl/glm-edge-1.5b-chat-mlx-4bit
Text Generation • 1B • Updated • 26