← Back to community benchmarks

gemma-4-12B-it

M2 Ultra (60c) · 64 GB · 8bit · 2026-06-04

Performance

64k

tokens

316.8

PP tok/s

31.4

TG tok/s

206884

TTFT (ms)

16.1

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 64 GB

GPU Cores 60

Software

oMLX v0.4.2.dev1

macOS macOS 26.5

Context 65,536