← Back to community benchmarks

gemma-4-26B-A4B-it-oQ4

M1 Max (32c) · 32 GB · 4bit · 2026-05-16

Performance

64k

tokens

401.1

PP tok/s

24.1

TG tok/s

163372

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.9.dev2

macOS macOS 15.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	654.1	56.3	14.4 GB	view
4k	716.0	53.8	15.1 GB	view
8k	622.9	50.3	15.3 GB	view
64k	401.1	24.1	18.2 GB	current