← Back to community benchmarks
gemma-4-31b-it
Performance
64k
tokens
193.2
PP tok/s
12.1
TG tok/s
339285
TTFT (ms)
45.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.11
macOS
macOS 26.5
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 246.4 | 18.3 | 31.8 GB | view |
| 4k | 252.8 | 17.8 | 34.5 GB | view |
| 8k | 249.8 | 17.3 | 35.0 GB | view |
| 16k | 240.1 | 16.3 | 36.9 GB | view |
| 32k | 222.3 | 14.6 | 39.0 GB | view |
| 64k | 193.2 | 12.1 | 45.8 GB | current |
| 128k | 150.0 | 8.1 | 57.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.3 | 1.00× |
| 2× | 30.1 | 1.64× |
| 4× | 32.0 | 1.75× |