Qwen3.8 27B
on M5 Max 128GB · AX Engine
Summary
User reports Qwen 3.8 27B AXQ MXFP4 MTP at 76.70 tok/s decode and 792.4 tok/s prefill on an M5 Max 128 GB.
Setup is AX Engine 7.5.3 with MXFP4 MTP weights, median of 20 runs on the flappy suite.
The same campaign measured the 6-bit pack at 76.04 / 768.7 and long_code at 72.71 / 856.9; MTPLX 2.11.2 reached 63.91 / 697.3 and mlx-lm 34.20 on the MXFP4 pack.