← Back to community benchmarks

gemma-4-31b-it-oQ8

M4 Max (40c) · 128 GB · 8bit · 2026-05-12
Performance
1k
tokens
193.8
PP tok/s
13.3
TG tok/s
5283
TTFT (ms)
31.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 193.8 13.3 31.8 GB current
4k 166.2 11.9 34.5 GB view