← Back to community benchmarks

gemma-4-26B-A4B-it-oQ6

M5 (10c) · 32 GB · 6bit · 2026-05-09

Performance

1k

tokens

645.8

PP tok/s

28.2

TG tok/s

1586

TTFT (ms)

20.2

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	645.8	28.2	20.2 GB	current
4k	709.7	26.3	20.8 GB	view
8k	692.5	23.9	21.0 GB	view
16k	675.8	22.8	21.5 GB	view
32k	445.5	12.2	22.5 GB	view
64k	283.4	7.5	23.7 GB	view