← Back to community benchmarks

gemma-4-12B-it

M5 Max (40c) · 128 GB · 4bit · 2026-06-05

Performance

4k

tokens

1,345

PP tok/s

39.6

TG tok/s

3045

TTFT (ms)

12.3

Peak mem (GB)

Hardware

Chip M5 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	861.9	40.6	11.3 GB	view
4k	1,345	39.6	12.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	40.6	1.00×
2×	69.3	1.71×
4×	97.4	2.40×