← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-04-15

Performance

1k

tokens

567.5

PP tok/s

63.6

TG tok/s

1804

TTFT (ms)

14.2

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.5.dev1

macOS macOS 15.7.5

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	63.6	1.00×
2×	84.8	1.33×
4×	97.8	1.54×