← Back to community benchmarks

gemma-4-26b-a4b-it-oQ8

M4 Pro (20c) · 64 GB · 8bit · 2026-05-06

Performance

64k

tokens

476.7

PP tok/s

26.4

TG tok/s

137485

TTFT (ms)

29.2

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.8

macOS macOS 26.3

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	355.6	44.2	26.2 GB	view
8k	724.6	42.6	26.6 GB	view
16k	648.5	39.8	26.7 GB	view
32k	560.0	34.9	27.5 GB	view
64k	476.7	26.4	29.2 GB	current
128k	356.2	17.1	32.7 GB	view