← Back to community benchmarks

gemma-4-31b-it

M2 Max (30c) · 64 GB · 4bit · 2026-04-03

Performance

64k

tokens

46.6

PP tok/s

5.6

TG tok/s

1406507

TTFT (ms)

33.6

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.3.1

macOS macOS 26.1

Context 65,536