← Back to community benchmarks
gemma-4-31b-it
Performance
1k
tokens
242.1
PP tok/s
22.1
TG tok/s
4229
TTFT (ms)
25.6
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 242.1 | 22.1 | 25.6 GB | current |
| 4k | 247.8 | 19.5 | 27.4 GB | view |