← Back to community benchmarks

gemma-4-31B-it-oQ6

M4 Max (40c) · 128 GB · 6bit · 2026-04-14
Performance
4k
tokens
195.0
PP tok/s
15.1
TG tok/s
21010
TTFT (ms)
27.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 26.3.1
Context 4,096