← Back to community benchmarks

gemma-4-31B-it-heretic-oQ4

M4 Max (40c) · 64 GB · 4bit · 2026-04-16

Performance

64k

tokens

154.7

PP tok/s

15.7

TG tok/s

423619

TTFT (ms)

33.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.5

macOS macOS 26.0.1

Context 65,536