M3 Max hits 70 tok/s locally, 32k task leaves 20GB RAM free
KaelinHooper · x · 2026-08-29
User benchmarks a local model on M3 Max (128GB): 70 tok/s inference, 300 tok/s prefill. A 32k token task left 20GB memory free, confirming usability for agents despite slightly lower intelligence than frontier models.
Related event: M3 Max Runs 125B Qwen Model Locally at 70 tok/s(3 posts)→
More from Infra
- NVIDIA and Sweden's Wallenberg launch Sferical One, a shared AI supercomputer — nvidia · 2026-10-16
- Next infra frontier: self-evolving systems that adapt and self-verify — _shreya_s · 2026-10-16
- Xiaomi's MiMo RL dashboard reveals $3.47M spent on just 30 training steps — bycloud · 2026-10-16
- Cerebras pushes disaggregated inference: heterogeneous prefill pools feeding wafer-scale decode — ai · 2026-10-16
- d-Matrix GA's Corsair rackscale, demos first public Attention-FFN disaggregation at 845 tok/s — ai · 2026-10-16
- Actual's inference engine hits 10k tok/s on NVIDIA DGX Station, GB300 case study — natesiggard · 2026-10-16