← Back to community benchmarks

gemma-4-31B-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-05-22
Performance
4k
tokens
619.2
PP tok/s
17.5
TG tok/s
6617
TTFT (ms)
28.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 583.7 18.1 25.5 GB view
4k 619.2 17.5 28.0 GB current
16k 560.5 15.3 29.5 GB view
64k 419.4 11.5 38.0 GB view