barrontang/gguf2mlx

Convert GGUF models into MLX-LM and mlx-vlm directories: adapter-based, fail-closed, no silent precision loss.

语言：Python · GitHub 星标：49 · Fork：7

话题：apple-silicon · gguf · mlx · mlx-lm · model-conversion · quantization · safetensors

在 GitHub 上查看原仓库