NVIDIA: Nemotron 3 Nano Omni (free)
🧠 AI Modelnvidia
Free multimodal 30B-A3B reasoning model for enterprise agent systems.
NVIDIA Nemotron 3 Nano Omni (30B-A3B) is a mixture-of-experts model with 30 billion total parameters and 3 billion activated per token. It supports multimodal inputs—text, audio, image, and video—and generates text outputs. The model is optimized for reasoning and tool use, with features like reasoning, temperature, top_p, seed, and tool integration. Its 256,000-token context window enables long-form understanding, making it suitable for complex enterprise agent pipelines. Released as an open model, it is freely accessible on OpenRouter, lowering barriers for developers and researchers.
💡Highlights
- ├─30B MoE, 3B activated per token
- ├─Multimodal: text, audio, image, video
- └─256K context, free on OpenRouter
🎯For
- ├─AI Researchers
- ├─Enterprise Developers
- └─Agent System Builders