Qwen3.8 27B
on M1 Ultra 64GB · oMLX
Use cases
codingvisionmath
Summary
User reports Qwen3.8-27B at 47-48 tok/s on an M1 Ultra 64GB.
Setup is oMLX 0.7.0 with oQ4e quant and MTP fixed depth 2.
MTP off gives 27.4 tok/s, adaptive depth 44.3 tok/s, and DFlash2 23.6 tok/s. The model is also used for vision, scoring 35/35 on a 35-item suite.