← Back to community benchmarks

gemma-4-12B-it-mxfp8

M5 Max (40c) · 64 GB · 8bit · 2026-06-09

Performance

16k

tokens

1,442

PP tok/s

35.0

TG tok/s

11361

TTFT (ms)

14.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.2

macOS macOS 26.5.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,276	44.0	12.6 GB	view
4k	1,560	35.7	13.7 GB	view
16k	1,442	35.0	14.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	44.0	1.00×
2×	38.0	0.86×
4×	44.8	1.02×