← Back to community benchmarks
NVIDIA-Nemotron-3-Nano-30B-A3B
Performance
64k
tokens
978.4
PP tok/s
71.5
TG tok/s
66984
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.18
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,094 | 124.3 | 18.8 GB | view |
| 4k | 1,284 | 118.9 | 19.9 GB | view |
| 64k | 978.4 | 71.5 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 124.3 | 1.00× |
| 2× | 178.5 | 1.44× |
| 4× | 217.1 | 1.75× |