← Back to community benchmarks

Gemma-4-31B

M3 Ultra (60c) · 256 GB · 6bit · 2026-06-04
Performance
16k
tokens
214.4
PP tok/s
11.0
TG tok/s
76403
TTFT (ms)
28.4
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 232.1 11.9 27.0 GB view
16k 214.4 11.0 28.4 GB current
64k 170.4 7.9 35.2 GB view