← Back to community benchmarks

gemma-4-26B-A4B-it-oQ5e

M1 Max (32c) · 32 GB · 5bit · 2026-05-18

Performance

64k

tokens

212.8

PP tok/s

15.9

TG tok/s

308004

TTFT (ms)

20.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 65,536