← Back to community benchmarks

gemma-4-31b-it-UD

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-05

Performance

128k

tokens

191.4

PP tok/s

5.3

TG tok/s

684903

TTFT (ms)

41.5

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.4

macOS macOS 26.4

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	333.0	21.2	24.2 GB	view
32k	300.5	13.7	27.3 GB	view
128k	191.4	5.3	41.5 GB	current