← Back to community benchmarks

gemma-4-31B-it-oQ4

M1 Max (24c) · 64 GB · 4bit · 2026-05-24
Performance
8k
tokens
90.4
PP tok/s
12.4
TG tok/s
90576
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 93.1 14.0 18.1 GB view
4k 92.0 13.1 20.7 GB view
8k 90.4 12.4 21.3 GB current
16k 88.8 11.1 22.4 GB view
32k 82.2 9.4 25.4 GB view
64k 71.1 6.1 31.4 GB view