← Back to community benchmarks

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

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

Performance

4k

tokens

918.7

PP tok/s

67.0

TG tok/s

4459

TTFT (ms)

26.1

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 4,096

Performance by Context Length

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