← Back to community benchmarks

gemma-4-31B-it

M5 Pro (20c) · 64 GB · 4bit · 2026-04-26
Performance
1k
tokens
333.6
PP tok/s
9.6
TG tok/s
3070
TTFT (ms)
27.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 9.6 1.00×
2× 17.0 1.77×
4× 23.5 2.45×
8× 26.9 2.80×