← Back to community benchmarks

gemma-4-12B

M4 Max (40c) · 128 GB · 8bit · 2026-06-04

Performance

4k

tokens

529.3

PP tok/s

32.0

TG tok/s

7740

TTFT (ms)

14.5

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.2.dev2

macOS macOS 26.5.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	524.6	27.0	13.2 GB	view
4k	529.3	32.0	14.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.0	1.00×
2×	25.7	0.95×
4×	46.6	1.73×