← Back to community benchmarks

gemma-4-31b-it

M4 Max (40c) · 128 GB · 8bit · 2026-04-25
Performance
8k
tokens
146.9
PP tok/s
8.3
TG tok/s
55761
TTFT (ms)
34.3
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 191.5 10.2 31.8 GB view
4k 140.4 9.4 33.6 GB view
8k 146.9 8.3 34.3 GB current
16k 138.3 6.0 35.4 GB view
Batching Results
Batch Size TG tok/s Speedup
10.2 1.00×
14.1 1.38×