← Back to community benchmarks

gemma-4-12B-it

M5 Max (40c) · 64 GB · 8bit · 2026-06-08

Performance

4k

tokens

1,689

PP tok/s

35.5

TG tok/s

2425

TTFT (ms)

14.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.2.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,513	36.9	12.8 GB	view
4k	1,689	35.5	14.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	36.9	1.00×
2×	63.0	1.71×
4×	85.8	2.33×