← Back to community benchmarks

gemma-4-12B-it-oQ8

M4 Max (40c) · 64 GB · 8bit · 2026-06-05

Performance

64k

tokens

411.5

PP tok/s

27.7

TG tok/s

159265

TTFT (ms)

16.2

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.2.dev2

macOS macOS 26.0.1

Context 65,536