← Back to community benchmarks

gemma-4-31b-it-oQ6

M3 Ultra (60c) · 256 GB · 6bit · 2026-05-25
Performance
64k
tokens
189.5
PP tok/s
14.5
TG tok/s
345805
TTFT (ms)
39.7
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.10
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 221.3 17.9 31.0 GB view
64k 189.5 14.5 39.7 GB current