←── back to feed
/topics/nvidia-nemotron-3-nano-omni-release

NVIDIA Nemotron 3 Nano Omni release

5 items1 sourcesupdated 2h agotrend 0

NVIDIA released Nemotron 3 Nano Omni on April 28, 2026, an open multimodal model that unifies vision, audio, and language capabilities into a single system for AI agents. The model achieves up to 9x efficiency gains by eliminating the need for separate models and context-switching overhead.

  • Released April 28, 2026 across Amazon SageMaker JumpStart, Hugging Face, and Together AI on day zero
  • Single unified model handles video, images, audio, and text — replacing separate vision, speech, and language models
  • Delivers up to 9x more efficient AI agents by reducing data passing and context loss between models
  • Designed for agentic workloads and enterprise use cases requiring long-context multimodal reasoning
  • Open model expanding NVIDIA's software and services offerings beyond hardware