← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-07
Performance
1k
tokens
249.4
PP tok/s
18.8
TG tok/s
4105
TTFT (ms)
34.6
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 249.4 18.8 34.6 GB current
4k 253.0 18.4 37.3 GB view
16k 243.0 16.7 39.3 GB view
32k 226.3 14.9 42.3 GB view
64k 197.6 10.6 48.6 GB view
128k 151.5 4.0 60.0 GB view
Batching Results
Batch Size TG tok/s Speedup
18.8 1.00×
31.7 1.69×
38.9 2.07×