← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 256 GB · 8bit · 2026-04-15
Performance
16k
tokens
236.0
PP tok/s
13.6
TG tok/s
69414
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 253.4 17.6 34.4 GB view
16k 236.0 13.6 35.4 GB current
64k 190.3 5.7 42.5 GB view