Nemotron Cascade 2 30B A3B
Nemotron Cascade 2 30B A3B is NVIDIA's language model. A 30B-parameter sparse MoE model in NVIDIA's Nemotron Cascade series, activating 3B parameters per token for efficient cascaded inference pipelines.
NVIDIA's language model. A 30B-parameter sparse MoE model in NVIDIA's Nemotron Cascade series, activating 3B parameters per token for efficient cascaded inference pipelines.Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Nemotron 4 15B | — | — | — | — | Available |
| Nemotron Super 3 120B | 256K | $0.150 | $0.650 | Available | |
| Nemotron Super 3 120B A12B | 262K | $0.090 | $0.450 | Available | |
| Nemotron Nano 3 30B | 262K | $0.060 | $0.240 | Available | |
| Nemotron 3 Nano 30B A3B | 262K | $0.050 | $0.200 | Available | |
| Nemotron 3 | — | — | — | — | Available |
| Nemotron 3 Super | — | — | — | — | Available |
| Nemotron 3 Super 120B | — | — | — | — | Available |
| Nemotron 3 Super 120B A12B | — | — | — | — | Available |
| Nemotron 2 Nano 12B VL | 131K | — | — | Available | |
| Nemotron Cascade 2 30B A3B | — | — | — | — | Current |