← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Max (38c) · 32 GB · 4bit · 2026-04-13

Performance

1k

tokens

537.9

PP tok/s

68.2

TG tok/s

1904

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 32 GB

GPU Cores 38

Software

oMLX v0.3.5.dev1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	537.9	68.2	14.2 GB	current
4k	602.1	59.7	14.8 GB	view
8k	614.6	40.5	15.0 GB	view
16k	574.6	25.4	15.4 GB	view
32k	470.4	7.2	16.0 GB	view