Qwen3.8 27B
on M3 Max · MLX
Summary
User reports Qwen3.8-27B at 31.1-33.3 tok/s with speculative decoding on an M3 Max.
Setup is MLX with 4-bit weights and k=3 draft tokens; plain decode without speculation gives 18.2-18.4 tok/s in Python and 19.1-19.4 tok/s in C++, with 84% acceptance and 3.49 tokens per pass.
Prefill is about 176-190 tok/s and peak memory is 16.3-16.9 GB. The M3 Max memory size is not stated.