← Back to community benchmarks
NVIDIA-Nemotron-3-Nano-30B-A3B
Performance
1k
tokens
998.7
PP tok/s
107.1
TG tok/s
1025
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.5
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 998.7 | 107.1 | 18.9 GB | current |
| 4k | 1,832 | 103.6 | 19.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 107.1 | 1.00× |
| 2× | 146.5 | 1.37× |
| 4× | 192.1 | 1.79× |