Qwen3 30B (3B active)
on M4 Pro 64GB · dasLLAMA
Summary
User reports Qwen3-30B-A3B-Instruct-2507 at 94.5 t/s generation and 806 t/s prompt processing on an M4 Pro with 64 GB unified memory.
Setup is dasLLAMA version 16 with Q4_K_M weights, f16 KV cache, and one Metal GPU, with 640 positions allocated.
The figures are native PP512 and TG128 means over five repetitions, not a single 512-input/128-output request.