← Back to community benchmarks

Gemma-4-31B

M3 Ultra (60c) · 256 GB · 6bit · 2026-06-04
Performance
4k
tokens
232.1
PP tok/s
11.9
TG tok/s
17645
TTFT (ms)
27.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 232.1 11.9 27.0 GB current
16k 214.4 11.0 28.4 GB view
64k 170.4 7.9 35.2 GB view