← Back to community benchmarks

gemma-4-31B-it-oQ4

M3 Ultra (80c) · 512 GB · 4bit · 2026-05-13
Performance
8k
tokens
330.9
PP tok/s
27.1
TG tok/s
24753
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.9.dev2
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 315.4 29.2 18.1 GB view
4k 332.2 28.4 20.7 GB view
8k 330.9 27.1 21.3 GB current
16k 308.3 25.2 22.4 GB view
32k 284.3 22.2 25.4 GB view
64k 235.7 17.4 31.3 GB view