← Back to community benchmarks

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

M1 Max (32c) · 32 GB · 4bit · 2026-05-03

Performance

4k

tokens

730.1

PP tok/s

53.5

TG tok/s

5610

TTFT (ms)

14.9

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 15.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	650.4	55.4	14.4 GB	view
4k	730.1	53.5	14.9 GB	current
8k	632.5	50.4	15.3 GB	view