← Back to community benchmarks

gemma-4-31b-it

M4 Max (40c) · 128 GB · 8bit · 2026-05-14
Performance
8k
tokens
198.8
PP tok/s
13.1
TG tok/s
41211
TTFT (ms)
35.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 198.8 13.1 35.7 GB current
16k 192.3 12.6 37.4 GB view
32k 179.8 11.8 39.2 GB view
64k 158.7 10.5 45.1 GB view