# Nemotron 3.5 Lightning 30B

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA.

The model employs a hybrid Mixture-of-Experts architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. The Lightning 3.5 model is released alongside a number of speculative decoding methods for faster text generation. The model has 3B active parameters and 30B parameters in total.

- **Model ID:** `nvidia/nemotron-3.5-lightning`
- **Type:** chat
- **Providers:** runinfra, deepinfra, fireworks
- **Context window:** 262,144
- **Maximum output tokens:** 131,072
- **Pricing:** $0.04/1M input tokens, $0.12/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/nemotron-3.5-lightning

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'nvidia/nemotron-3.5-lightning',
  prompt: 'Why is the sky blue?'
})
```

## Links

- [Model page](https://vercel.com/ai-gateway/models/nemotron-3.5-lightning)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://runinfra.ai/inference/nemotron-3-5-lightning-30b)