MLX-Serve adds Inkling 2 Mini with ~24 custom kernels, fastest Mac inference yet

SumitGup · x · 2026-11-23

ddalcu announced MLX-Serve support for Inkling 2 Mini, claiming 24 custom kernels make it possibly the fastest way to run the model on a Mac today. Quantization support covers 8-bit plus NVFP4 and MXFP8; 4-bit hasn't passed their quality bar yet. ivanfioravanti is separately optimizing for M3 Ultra.

Original post →

More from Infra

Infra channel →