← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Ultra (60c) · 256 GB · bf16 · 2026-05-14

Performance

4k

tokens

1,545

PP tok/s

63.5

TG tok/s

2651

TTFT (ms)

48.5

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.3.8

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,218	65.4	47.8 GB	view
4k	1,545	63.5	48.5 GB	current
8k	1,611	61.0	48.6 GB	view
16k	1,575	56.7	49.1 GB	view
32k	1,442	49.6	50.0 GB	view
64k	1,192	39.0	51.2 GB	view
128k	847.5	26.9	54.8 GB	view