← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Ultra (76c) · 128 GB · 4bit · 2026-04-03

Performance

64k

tokens

911.1

PP tok/s

23.3

TG tok/s

71927

TTFT (ms)

18.8

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 128 GB

GPU Cores 76

Software

oMLX v0.3.2

macOS macOS 26.4

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	1,191	53.1	15.9 GB	view
16k	1,163	45.1	16.3 GB	view
32k	1,082	34.3	17.1 GB	view
64k	911.1	23.3	18.8 GB	current