← Back to community benchmarks

gemma-4-31b-it-UD

M4 Max (32c) · 36 GB · 4bit · 2026-05-06
Performance
1k
tokens
158.8
PP tok/s
14.5
TG tok/s
6449
TTFT (ms)
22.1
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024