← Back to community benchmarks
NVIDIA-Nemotron-3-Nano-30B-A3B
Performance
4k
tokens
764.4
PP tok/s
92.6
TG tok/s
5359
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.14
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 644.3 | 96.0 | 18.2 GB | view |
| 4k | 764.4 | 92.6 | 18.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.0 | 1.00× |
| 2× | 133.4 | 1.39× |
| 4× | 163.8 | 1.71× |