← Back to community benchmarks
gemma-4-31B-it-OptiQ
Performance
32k
tokens
227.7
PP tok/s
20.7
TG tok/s
143896
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 227.7 | 20.7 | 24.4 GB | current |
| 64k | 197.7 | 15.6 | 32.4 GB | view |