← Back to community benchmarks

gemma-4-12B-it

M3 Max (40c) · 128 GB · 4bit · 2026-07-23

Performance

64k

tokens

155.9

PP tok/s

11.7

TG tok/s

420405

TTFT (ms)

10.5

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 65,536