← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 256 GB · 4bit · 2026-05-11
Performance
64k
tokens
199.0
PP tok/s
17.6
TG tok/s
329373
TTFT (ms)
30.9
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 228.0 22.7 22.8 GB view
64k 199.0 17.6 30.9 GB current
128k 154.7 12.1 42.8 GB view
195k 124.7 8.5 57.9 GB view