← Back to community benchmarks

gemma-4-31b-it

M5 (10c) · 32 GB · 4bit · 2026-05-18
Performance
1k
tokens
184.7
PP tok/s
7.0
TG tok/s
5544
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 184.7 7.0 17.4 GB current
32k 149.2 5.1 23.6 GB view
Batching Results
Batch Size TG tok/s Speedup
7.0 1.00×
13.2 1.89×
15.6 2.23×