← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 4bit · 2026-04-13

Performance

1k

tokens

1,766

PP tok/s

113.9

TG tok/s

580

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.5.dev1

macOS macOS 26.4

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	113.9	1.00×
2×	170.1	1.49×
4×	230.8	2.03×