M3 Max 128GB

Name: M3 Max 128GB local LLM performance reports
Creator: llamaperf
License: https://creativecommons.org/licenses/by/4.0/

APPLE · 128GB unified memory · 1 report

This page is thin (1 of 3 reports needed for indexing). Help fill it in.

Latest Most reported Fastest t/s

Qwen3.6 27B

M3 Max 128GB · MLX · 290,000 ctx

throughput:: 5.5 t/s gen · 160.0 t/s pp
quant:: Q8 (mlx)

long-context

User reports 160 tok/s prefill, 5-6 tok/s generation on M5 Max 128GB with Qwen 3.6 27B Q8 MLX at 290k context. GPU utilization only 36-50%, feels off compared to expected 8-14 tok/s generation. Asks for comparison with other setups.