← Back to community benchmarks

gemma-4-12B-it

M4 Pro (20c) · 48 GB · 8bit · 2026-06-04

Performance

1k

tokens

262.4

PP tok/s

17.5

TG tok/s

3902

TTFT (ms)

12.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.4.2.dev2

macOS macOS 15.7.7

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	262.4	17.5	12.8 GB	current
4k	264.3	16.0	13.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.5	1.00×
2×	29.4	1.68×
4×	39.6	2.26×