← Back to community benchmarks

gemma-4-31b-it

M4 Max (40c) · 64 GB · 4bit · 2026-05-12
Performance
8k
tokens
198.4
PP tok/s
22.7
TG tok/s
41283
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 201.4 24.1 17.6 GB view
4k 200.7 23.5 20.2 GB view
8k 198.4 22.7 20.7 GB current
16k 191.0 21.1 21.9 GB view
32k 178.3 18.8 24.9 GB view
64k 157.6 15.3 30.9 GB view
Batching Results
Batch Size TG tok/s Speedup
24.1 1.00×
41.0 1.70×
45.8 1.90×