← Back to community benchmarks

MiniMax-M3

M3 Ultra (80c) · 512 GB · 4bit · 2026-07-23

Performance

64k

tokens

292.4

PP tok/s

17.1

TG tok/s

224162

TTFT (ms)

242.9

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.4.5.dev1

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	355.1	29.1	226.6 GB	view
4k	365.7	19.9	227.7 GB	view
8k	336.7	19.6	228.0 GB	view
16k	336.5	19.1	230.2 GB	view
32k	324.9	18.4	234.4 GB	view
64k	292.4	17.1	242.9 GB	current