← Back to community benchmarks
Nemotron-3-Nano-30B-A3B-TurboQuant
Performance
1k
tokens
1,372
PP tok/s
67.4
TG tok/s
747
TTFT (ms)
33.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,372 | 67.4 | 33.7 GB | current |
| 4k | 1,812 | 63.5 | 34.8 GB | view |
| 8k | 1,894 | 64.6 | 34.9 GB | view |
| 32k | 4,991 | 65.4 | 34.8 GB | view |
| 64k | 4,057 | 63.8 | 34.9 GB | view |
| 128k | 2,728 | 60.2 | 37.8 GB | view |
| 195k | 2,061 | 56.9 | 41.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 67.4 | 1.00× |
| 2× | 89.2 | 1.32× |
| 4× | 109.7 | 1.63× |
| 8× | 218.7 | 3.24× |