← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (20c) · 64 GB · 8bit · 2026-05-30

Performance

64k

tokens

1,343

PP tok/s

30.4

TG tok/s

48808

TTFT (ms)

30.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.12

macOS macOS 26.5

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	1,699	38.8	27.5 GB	view
64k	1,343	30.4	30.0 GB	current
128k	936.1	21.2	34.2 GB	view
195k	691.9	16.2	35.9 GB	view