← Back to community benchmarks

gemma-4-31b-it

M5 (10c) · 32 GB · 4bit · 2026-04-16
Performance
1k
tokens
159.1
PP tok/s
6.9
TG tok/s
6437
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 159.1 6.9 17.4 GB current
4k 152.0 6.4 19.2 GB view
Batching Results
Batch Size TG tok/s Speedup
6.9 1.00×
11.4 1.65×
7.8 1.13×