← Back to community benchmarks

Gemma-4-Garnet-V2-31B-it-ultra-uncensored-heretic-oQ4

M5 Pro (20c) · 48 GB · 4bit · 2026-05-23

Performance

1k

tokens

364.0

PP tok/s

13.3

TG tok/s

2814

TTFT (ms)

18.1

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	364.0	13.3	18.1 GB	current
4k	373.5	13.5	20.7 GB	view
64k	270.4	8.1	29.1 GB	view