Model2h ago
Nvidia Releases Nemotron 3 Nano Omni Model
Nvidia launched Nemotron 3 Nano Omni, an open multimodal model processing text, image, video, and audio. The company disclosed its training data sources, citing Qwen, GPT-OSS, Kimi, and DeepSeek OCR. This transparency reveals the reliance on existing open-weights datasets. Developers now have a concrete blueprint for building compact, high-performance multimodal systems.