← Back to community benchmarks
gemma-4-31B-it
Performance
4k
tokens
245.9
PP tok/s
16.8
TG tok/s
16656
TTFT (ms)
33.6
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 240.8 | 18.1 | 31.8 GB | view |
| 4k | 245.9 | 16.8 | 33.6 GB | current |
| 8k | 248.9 | 14.4 | 34.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.1 | 1.00× |
| 2× | 30.7 | 1.70× |
| 4× | 37.9 | 2.09× |
| 8× | 43.0 | 2.38× |