← Back to community benchmarks

gemma-4-12B-it

M5 Pro (16c) · 48 GB · 8bit · 2026-06-04

Performance

1k

tokens

678.7

PP tok/s

19.1

TG tok/s

1509

TTFT (ms)

12.8

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.4.2.dev1

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	678.7	19.1	12.8 GB	current
4k	772.9	18.4	13.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	19.1	1.00×
2×	31.5	1.65×
4×	40.2	2.10×