← Back to community benchmarks

gemma-4-31B-it-RotorQuant

M4 Max (32c) · 36 GB · 4bit · 2026-06-12

Performance

4k

tokens

154.7

PP tok/s

18.1

TG tok/s

26472

TTFT (ms)

19.9

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.4.4rc1

macOS macOS 27.0

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	158.7	18.5	17.8 GB	view
4k	154.7	18.1	19.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.5	1.00×
2×	33.3	1.80×
4×	68.2	3.69×