← Back to community benchmarks

gemma-4-26b-a4b-it

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

Performance

16k

tokens

1,566

PP tok/s

56.9

TG tok/s

10462

TTFT (ms)

48.7

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.3.8

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	593.7	63.6	48.3 GB	view
8k	1,613	61.1	48.6 GB	view
16k	1,566	56.9	48.7 GB	current
32k	1,440	49.4	49.5 GB	view
64k	1,176	38.8	51.2 GB	view