← Back to community benchmarks

gemma-4-31b

M5 Max (40c) · 128 GB · 8bit · 2026-04-07
Performance
128k
tokens
204.9
PP tok/s
2.2
TG tok/s
639771
TTFT (ms)
51.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.4
Context 131,072