← Back to community benchmarks
gemma-4-31b-it-mxfp8
Performance
4k
tokens
245.6
PP tok/s
16.8
TG tok/s
16679
TTFT (ms)
32.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 240.2 | 18.3 | 30.9 GB | view |
| 4k | 245.6 | 16.8 | 32.8 GB | current |