← Back to community benchmarks

gemma-4-31b-it

M5 (10c) · 32 GB · 4bit · 2026-04-04
Performance
4k
tokens
163.0
PP tok/s
5.8
TG tok/s
25122
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.2
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 175.8 5.9 18.8 GB view
4k 163.0 5.8 20.5 GB current
Batching Results
Batch Size TG tok/s Speedup
5.9 1.00×
11.6 1.97×
9.6 1.63×