← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 96 GB · 4bit · 2026-04-06
Performance
64k
tokens
196.8
PP tok/s
3.0
TG tok/s
333017
TTFT (ms)
50.7
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 226.5 7.8 46.0 GB view
64k 196.8 3.0 50.7 GB current