← Back to community benchmarks

gemma-4-31B-it

M4 Max (40c) · 64 GB · 4bit · 2026-05-19
Performance
16k
tokens
100.2
PP tok/s
7.3
TG tok/s
163514
TTFT (ms)
31.6
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 195.2 15.5 27.3 GB view
4k 166.6 14.4 29.9 GB view
8k 158.3 12.8 30.4 GB view
16k 100.2 7.3 31.6 GB current
Batching Results
Batch Size TG tok/s Speedup
15.5 1.00×
13.2 0.85×
17.4 1.12×
20.8 1.34×