← Back to community benchmarks

gemma-4-31b-it

M5 Max (40c) · 128 GB · 4bit · 2026-05-11
Performance
195k
tokens
277.4
PP tok/s
7.4
TG tok/s
720959
TTFT (ms)
57.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 569.8 17.5 22.8 GB view
64k 470.8 14.5 30.8 GB view
128k 357.7 9.8 42.8 GB view
195k 277.4 7.4 57.8 GB current