← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (16c) · 48 GB · 4bit · 2026-05-05

Performance

1k

tokens

577.8

PP tok/s

66.0

TG tok/s

1772

TTFT (ms)

14.3

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	577.8	66.0	14.3 GB	current
4k	610.8	62.5	14.9 GB	view
8k	604.8	59.6	15.3 GB	view
16k	576.6	52.2	15.6 GB	view
32k	516.5	40.3	16.5 GB	view
64k	428.9	25.7	17.7 GB	view
128k	311.1	12.5	21.2 GB	view