← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-24
Performance
128k
tokens
285.9
PP tok/s
7.3
TG tok/s
458392
TTFT (ms)
57.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 613.0 15.3 31.8 GB view
4k 659.5 14.9 34.5 GB view
8k 622.1 14.6 35.0 GB view
16k 568.6 13.8 36.1 GB view
32k 511.3 12.4 39.0 GB view
64k 415.1 10.3 45.1 GB view
128k 285.9 7.3 57.1 GB current
195k 203.3 5.7 72.1 GB view
Batching Results
Batch Size TG tok/s Speedup
15.3 1.00×
22.5 1.47×
29.2 1.91×
34.7 2.27×