← Back to community benchmarks

gemma-4-26b-a4b-it-mxfp8

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-13

Performance

64k

tokens

1,189

PP tok/s

44.6

TG tok/s

55121

TTFT (ms)

29.3

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,310	82.2	25.1 GB	view
4k	1,633	79.1	25.7 GB	view
8k	1,673	75.3	25.9 GB	view
16k	1,606	69.1	26.3 GB	view
32k	1,454	59.2	27.3 GB	view
64k	1,189	44.6	29.3 GB	current