Dev runs 125B Qwen model locally on M3 Max at 70 tok/s via MLX
mayfer · x · 2026-08-28
A developer verified the native performance of Qwen 3.8 Flash Next (125B-A6B) on Apple Silicon using mlx-serve. On an M3 Max (128GB), the setup achieved 70 tok/s serial decoding and 300 tok/s prefill, successfully handling 32k token tasks with 20GB memory remaining.
The implementation uses Zig + Metal without Python. Key optimizations include hyper-connection residual streams, n-gram embeddings gathered directly from disk, sparse attention past 2k tokens, and 5 new Metal kernels. The model also supports image and video input.
Related event: M3 Max Runs 125B Qwen Model Locally at 70 tok/s(3 posts)→
More from Infra
- How Microsoft optimized Windows for Nvidia's Arm-based RTX Spark AI laptops — tomwarren · 2026-10-15
- How Microsoft optimized Windows for Nvidia's Arm-based RTX Spark laptops — The Verge AI · 2026-10-15
- Global smartphone shipments plunge 22% in worst quarterly decline on record as AI demand fuels memory costs — Polymarket · 2026-10-15
- SK Hynix drops 11% again, now below 3x FY2027 earnings as AI memory selloff deepens — JOBhakdi · 2026-10-15
- ASML Sells Zero Lithography Machines into Europe as US Hosts 75%+ of AI Compute — NinaDSchick · 2026-10-15
- Nvidia quietly reclassified SPCX as 'Hyperscale', signaling deeper neocloud reliance — RihardJarc · 2026-10-15