4 projects
mlx-quant-fidelity
Measure MLX quantization quality loss — KL divergence, perplexity, top-token agreement for KV cache and weights
mlx-model-doctor
Validate MLX model repositories before loading them.
mlx-taef
Tiny AutoEncoders for diffusion on Apple Silicon — live previews + low-memory decode for FLUX, SD, and Qwen-Image.
mlx-teacache
TeaCache step-skipping for FLUX, Qwen-Image & Z-Image diffusion on Apple Silicon, in pure MLX
