← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 4bit · 2026-04-19

Performance

1k

tokens

1,136

PP tok/s

113.3

TG tok/s

902

TTFT (ms)

14.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,136	113.3	14.0 GB	current
4k	1,387	97.9	14.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	113.3	1.00×
2×	163.1	1.44×
4×	209.4	1.85×