← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (80c) · 512 GB · 6bit · 2026-04-18
Performance
1k
tokens
312.1
PP tok/s
22.0
TG tok/s
3281
TTFT (ms)
24.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 312.1 22.0 24.7 GB current
4k 323.0 20.8 26.5 GB view
8k 324.6 19.0 26.8 GB view
16k 313.0 16.3 27.6 GB view
32k 293.4 12.9 29.9 GB view
64k 252.5 8.8 34.6 GB view