← Back to community benchmarks

gemma-4-31B-it-oQ4

M1 Max (24c) · 64 GB · 4bit · 2026-06-13
Performance
8k
tokens
88.6
PP tok/s
11.5
TG tok/s
92447
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.4.4rc1
macOS macOS 26.5.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 94.4 14.3 18.3 GB view
4k 90.0 13.3 20.8 GB view
8k 88.6 11.5 21.3 GB current
16k 88.7 11.5 22.8 GB view
32k 80.8 9.7 26.0 GB view