← Back to community benchmarks

gemma-4-31b-it

M1 Max (32c) · 64 GB · 6bit · 2026-04-05

Performance

16k

tokens

69.6

PP tok/s

5.8

TG tok/s

235366

TTFT (ms)

27.6

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.4

macOS macOS 26.3.1

Context 16,384