NVIDIA's NEW Open Multimodal Intelligence - Nemotron 3 Nano Omni

In this video, we look at the latest Nemotron model from Nvidia, Nemotron 3 Nano Omni, which is a multi-modal model which is built to be small, fast, and fully multi-modal for agents supporting text, images, videos and audio. Blog: https://developer.nvidia.com/blog/nvidia-nemotron-3-nano-omni-powers-multimodal-agent-reasoning-in-a-single-efficient-open-model/ HF Blog: https://huggingface.co/blog/nvidia/nemotron-3-nano-omni-multimodal-intelligence HF Model: https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 Twitter: https://x.com/Sam_Witteveen 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: https://drp.li/dIMes 👨‍💻Github: https://github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro 00:12 NVIDIA models released in the past 00:59 Nemotron 3 Nano Omni 02:26 PinchBench 03:31 Nemotron 3 Nano Omni Paper 04:16 Nemotron 3 Nano Paper 05:28 Nemotron 3 Nano Omni Hugging Face 05:50 OpenRouter and NVIDIA Cloud 06:25 Demo