← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · 4bit · 2026-05-03
Performance
16k
tokens
571.5
PP tok/s
15.1
TG tok/s
28668
TTFT (ms)
31.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 571.7 16.3 27.3 GB view
4k 613.4 16.9 29.9 GB view
8k 609.5 16.3 30.4 GB view
16k 571.5 15.1 31.6 GB current
32k 529.2 13.6 34.4 GB view
64k 445.8 11.2 40.5 GB view
Batching Results
Batch Size TG tok/s Speedup
16.3 1.00×
28.3 1.74×
38.1 2.34×
44.7 2.74×