Qwen3.6 35B (3B active)
on M4 Max 128GB · oMLX
Sep 7, 2026
Summary
User benchmarks Qwen3.6-35B-A3B on a Mac with OMLX, comparing MTP enabled against disabled.
MTP shows minimal speedup for the 35B MoE model but roughly 2x for the 27B dense model.
Results include pp and tg t/s at various context lengths and batch sizes.