← Back to community benchmarks

gemma-4-31B-it

M5 Pro (20c) · 64 GB · 4bit · 2026-04-25

Performance

1k

tokens

330.2

PP tok/s

8.9

TG tok/s

3101

TTFT (ms)

27.3

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	330.2	8.9	27.3 GB	current
4k	333.3	8.7	29.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	8.9	1.00×
2×	16.4	1.84×
4×	21.5	2.42×