Qwen3.8 27B
on M5 Max · MTPLX
Use cases
codingchat
Summary
User reports Qwen3.8 27B Bare Speed at 65.2 tok/s on an M5 Max MacBook Pro.
Setup is MTPLX with a flat 4-bit MLX quant and MTP speculative decoding at depth 3, single stream, 16.0 GB download and 17.0 GB peak unified memory.
A 52,740-token answer sustained 32.4 tok/s over 27.2 minutes; long reasoning at xhigh ran 35.7 and 32.0 tok/s. The same task in the MTPLX Mac app ran 64.4 tok/s, oMLX 0.5.7 ran 63.3 tok/s and LM Studio ran 17.40 tok/s on the long answer. KL divergence to the bf16 checkpoint is 0.0376.