← Back to community benchmarks

gemma-4-31b-it

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

Performance

1k

tokens

328.4

PP tok/s

29.1

TG tok/s

3118

TTFT (ms)

17.6

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.5.dev1

macOS macOS 26.2

Context 1,024