Qwen3.6 35B (3B active)
on M3 Max 36GB · mlx_lm.server
Summary
User benchmarks Qwen3.6-35B-A3B at 41.5 tok/s single-stream decode on an Apple M3 Max 36GB.
Setup is mlx_lm.server with 4-bit MLX weights and continuous batching; prefill at 1k input is 919 tok/s.
Decode peaks at 95 tok/s at 8 concurrent requests. Schema following scored 1.00, GSM8K 0.95 and IFEval 0.82 over 40 items.