← Back to community benchmarks

gemma-4-31B-it

M3 Ultra (80c) · 512 GB · 8bit · 2026-05-23

Performance

64k

tokens

251.7

PP tok/s

13.1

TG tok/s

260404

TTFT (ms)

41.8

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.9

macOS macOS 26.4.1

Context 65,536