← Back to community benchmarks

gemma-4-26B-A4B-it-qat

M2 Max (30c) · 64 GB · 8bit · 2026-07-24

Performance

4k

tokens

501.3

PP tok/s

48.1

TG tok/s

8171

TTFT (ms)

26.1

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.5.1

macOS macOS 15.7.7

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	501.3	48.1	26.1 GB	current
16k	477.0	42.5	26.7 GB	view
64k	392.3	28.7	29.2 GB	view