← Back to community benchmarks

gemma-4-26B-A4B-it-oQ6

M3 Max (40c) · 64 GB · 6bit · 2026-05-10

Performance

64k

tokens

799.8

PP tok/s

40.7

TG tok/s

81940

TTFT (ms)

23.7

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 15.7.4

Context 65,536