M3 Max Runs 125B Qwen Model Locally at 70 tok/s

Tests show the Qwen 3.8 Flash Next (125B-A6B) model running natively on an M3 Max (128GB) via mlx-serve at 70 tok/s inference, with 20GB memory still free after 32k-token tasks, despite some thermal throttling.

2026-08-28 ~ 2026-08-29 · 3 related posts

• Dev runs 125B Qwen model locally on M3 Max at 70 tok/s via MLX — mayfer · 2026-08-28
• M3 Max achieves 70 tok/s locally with 20GB RAM free after 32k task — mayfer · 2026-08-28

1 near-duplicate retellings: KaelinHooper