NVIDIA Releases Nemotron 3 Nano Omni: 30B Multimodal MoE Supporting Documents, Audio, and Video

Summary

NVIDIA released Nemotron 3 Nano Omni on April 28, 2026, a 30-billion-parameter multimodal mixture-of-experts model supporting text, image, video, audio, and document inputs with a 256K context window. The model saw immediate adoption across Ollama, LM Studio, and OpenRouter within hours of release, indicating strong developer community interest in locally deployable multimodal models. Weights are available on Hugging Face under an open license. The model is positioned for agentic applications r