← Back to community benchmarks

gemma-4-26B-A4B-it-oQ3

M1 Max (32c) · 32 GB · 3bit · 2026-05-03

Performance

8k

tokens

664.9

PP tok/s

48.6

TG tok/s

12321

TTFT (ms)

12.3

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 15.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	619.8	52.9	11.4 GB	view
4k	738.2	51.6	11.9 GB	view
8k	664.9	48.6	12.3 GB	current