← Back to community benchmarks

gemma-4-26b-a4b-it-oQ4

M1 Max (32c) · 32 GB · 4bit · 2026-05-26

Performance

32k

tokens

645.8

PP tok/s

36.6

TG tok/s

50741

TTFT (ms)

16.1

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.11

macOS macOS 26.5

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	638.3	56.3	14.4 GB	view
4k	743.2	54.4	15.0 GB	view
32k	645.8	36.6	16.1 GB	current
64k	489.0	23.4	17.7 GB	view