← Back to community benchmarks

gemma-4-31B-it

M3 Ultra (80c) · 512 GB · 8bit · 2026-05-01
Performance
16k
tokens
320.3
PP tok/s
14.1
TG tok/s
51151
TTFT (ms)
34.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 320.3 14.1 34.7 GB current
32k 298.7 11.4 37.0 GB view
64k 256.7 8.2 41.8 GB view