← Back to community benchmarks

gemma-4-31B

M1 Max (32c) · 64 GB · 6bit · 2026-05-13

Performance

64k

tokens

46.8

PP tok/s

3.8

TG tok/s

1400108

TTFT (ms)

34.6

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 26.3.1

Context 65,536