← Back to community benchmarks

gemma-4-26B-A4B-it-RotorQuant

M2 Ultra (60c) · 192 GB · 8bit · 2026-05-05

Performance

1k

tokens

799.2

PP tok/s

73.6

TG tok/s

1281

TTFT (ms)

25.7

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 192 GB

GPU Cores 60

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	799.2	73.6	25.7 GB	current
4k	918.7	67.0	26.1 GB	view
64k	757.2	10.2	29.2 GB	view