← Back to community benchmarks

gemma-4-12B-it

M5 Max (40c) · 128 GB · 8bit · 2026-06-05

Performance

1k

tokens

1,381

PP tok/s

43.3

TG tok/s

742

TTFT (ms)

13.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.2.dev2

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,381	43.3	13.2 GB	current
4k	1,434	23.1	14.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	43.3	1.00×
2×	35.0	0.81×
4×	52.0	1.20×