Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

NVIDIA has unveiled Nemotron 3 Nano Omni, a new omni-modal understanding model built for real-world document analysis, multiple image reasoning, automatic speech recognition, long audio-video understanding, agentic computer use, and general reasoning. It extends the Nemotron line from a vision-language system to a broader text+image+video+audio model. The architecture combines the Nemotron 3 hybrid Mamba-Transformer Mixture-of-Experts backbone with a C-RADIOv4-H vision encoder and Parakeet-TDT-0.6B-v2 audio encoder, designed to preserve fine visual detail and scale to very long multimodal contexts for dense images, documents, and videos.

Nemotron 3 Nano Omni delivers best-in-class accuracy on complex document intelligence leaderboards such as MMlongBench-Doc and OCRBenchV2, while also leading in video and audio leaderboards like WorldSense and DailyOmni. It achieves top accuracy on VoiceBench for audio understanding and ranks as the most cost-efficient open video understanding model on MediaPerf. The model delivers up to 9x higher throughput and 2.9x the single-stream reasoning speed on multimodal use-cases compared to alternatives. It also leads the open-weights Qwen3-Omni in many domains, including document understanding (MMLongBench-Doc: 57.5 vs 49.5), video understanding (Video-MME: 72.2 vs 70.5), and audio understanding (VoiceBench: 89.4 vs 88.8). The training recipe uses staged multimodal alignment and context extension, followed by preference optimization and multimodal reinforcement learning.