← Back to community benchmarks

gemma-4-26B-A4B-it

M2 Pro (19c) · 32 GB · 4bit · 2026-05-26

Performance

1k

tokens

300.5

PP tok/s

44.7

TG tok/s

3408

TTFT (ms)

14.3

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 32 GB

GPU Cores 19

Software

oMLX v0.3.10

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	300.5	44.7	14.3 GB	current
4k	322.7	43.1	14.6 GB	view
8k	321.6	41.0	14.8 GB	view
16k	312.3	37.3	15.2 GB	view
32k	291.0	32.1	16.0 GB	view
64k	253.3	24.5	17.7 GB	view