Qwen3 14B
on M5 Ultra 256GB · LM Studio
Summary
User reports Qwen3-14B at 80.3 t/s on a Mac Studio M5 Ultra with 256 GB unified memory.
Setup is LM Studio with 4-bit MLX weights on one machine, 36 CPU cores and 80 GPU cores.
The 80.3 t/s is the mean of three runs; TTFT is 3.53 seconds, and the displayed 2,754 prompt tokens/s is prompt-token count divided by TTFT, not native prefill. Configured context capacity is unknown.