← Back to community benchmarks

MiniMax-M2.7-4bit-DWQ

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-16

Performance

32k

tokens

440.0

PP tok/s

15.2

TG tok/s

74465

TTFT (ms)

128.4

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.5

macOS macOS 26.3.1

Context 32,768