← Back to community benchmarks

gemma-4-31B-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-05-22
Performance
16k
tokens
560.5
PP tok/s
15.3
TG tok/s
29235
TTFT (ms)
29.5
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 16,384
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 view
16k 560.5 15.3 29.5 GB current
64k 419.4 11.5 38.0 GB view