Nemotron 3.5 Lightning 30B
Nemotron 3.5 Lightning 30B is NVIDIA's language model with a 1.0M context window and up to 33K output tokens. A hybrid Mixture-of-Experts LLM with interleaved Mamba-2 and MoE layers, built for reasoning and tool-use workloads with implicit caching support.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Nemotron 4 15B | — | — | — | — | Available |
| Nemotron 3.5 Lightning 30B | 1.0M | — | — | Current | |
| Nemotron Lightning 3.5 | 1.0M | $0.050 | $0.200 | Available | |
| Nemotron 3 Ultra 550B A55B | 1.0M | $0.250 | $2.15 | Deprecated | |
| Nemotron 3.5 Content Safety | 131K | $0.200 | $0.200 | Available | |
| Nemotron Nano 3 30B A3B Omni Reasoning | 256K | — | — | Available | |
| Nemotron Super 3 120B | 256K | $0.150 | $0.650 | Available | |
| Nemotron Nano 3 30B | 262K | $0.060 | $0.240 | Available | |
| Nemotron Nano 3 30B A3B Reasoning | — | — | — | — | Available |
| Nemotron Nano 3 30B A3B Omni | — | — | — | — | Available |
| Nemotron Nano 3 4B | — | — | — | — | Available |