← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · 4bit · 2026-04-24

Performance

195k

tokens

2,516

PP tok/s

39.7

TG tok/s

79502

TTFT (ms)

24.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7rc2

macOS macOS 26.4.1

Context 200,000