← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · unknown · 2026-04-07
Performance
16k
tokens
575.7
PP tok/s
6.0
TG tok/s
28461
TTFT (ms)
63.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 541.7 7.3 61.1 GB view
4k 635.2 7.2 62.9 GB view
8k 620.9 6.9 63.0 GB view
16k 575.7 6.0 63.9 GB current
Batching Results
Batch Size TG tok/s Speedup
7.3 1.00×
7.4 1.01×
15.2 2.08×