← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (80c) · 512 GB · 8bit · 2026-04-16

Performance

128k

tokens

163.6

PP tok/s

4.9

TG tok/s

800994

TTFT (ms)

51.3

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.5.dev1

macOS macOS 26.3.1

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	256.4	7.9	41.7 GB	view
128k	163.6	4.9	51.3 GB	current