← Back to community benchmarks

gemma-4-31b-it

M4 Max (40c) · 128 GB · 4bit · 2026-05-18
Performance
64k
tokens
157.0
PP tok/s
15.6
TG tok/s
417305
TTFT (ms)
27.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4
Context 65,536