Qwen3.6 35B (3B active)
on M5 Max · MLX
Use cases
codingvisionsummarizationagenticlong-context
Summary
User reports Qwen 3.6 35B-A3B at 130-140 t/s on an M5 Max at 4-bit.
Setup uses MLX and llama.cpp engines in a local AI app for macOS.
on M5 Max · MLX