← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 96 GB · 4bit · 2026-05-04
Performance
4k
tokens
255.5
PP tok/s
29.7
TG tok/s
16031
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 254.0 31.2 17.6 GB view
4k 255.5 29.7 20.2 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 31.2 1.00×
2× 47.2 1.51×
4× 53.8 1.72×