Qwen3.6-35B-A3B-4bit, 64k context, M4 Pro Mac mini using speculative prefill:
Prefill: ~1500 tok/s
Decode: ~65-75 tok/s
Super consistent perf compared to out of box mlx that throttles under sustained load. Built a custom harness to do chat loop testing on extended sessions.
ALT local llm mlx performance comparision with prefill optimization on a mac mini