← Back to community benchmarks

gemma-4-31b-it

M4 Pro (16c) · 64 GB · 8bit · 2026-05-15
Performance
8k
tokens
79.3
PP tok/s
3.7
TG tok/s
103346
TTFT (ms)
35.0
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 64 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 81.7 7.0 31.8 GB view
4k 76.9 6.9 34.5 GB view
8k 79.3 3.7 35.0 GB current
Batching Results
Batch Size TG tok/s Speedup
7.0 1.00×
13.2 1.89×