← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-25

Performance

64k

tokens

1,343

PP tok/s

38.7

TG tok/s

48790

TTFT (ms)

30.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.10

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,068	76.7	25.8 GB	view
4k	1,704	78.0	26.4 GB	view
8k	1,959	75.1	26.6 GB	view
16k	1,969	66.8	27.1 GB	view
32k	1,749	54.7	28.0 GB	view
64k	1,343	38.7	30.0 GB	current