← Back to community benchmarks

gemma-4-26B-A4B-it-heretic

M1 Max (24c) · 32 GB · 4bit · 2026-07-12

Performance

64k

tokens

305.7

PP tok/s

22.5

TG tok/s

214371

TTFT (ms)

17.7

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 65,536