NVIDIA Releases Nemotron 3.5 Super VL Open Model
A sparse 120B architecture with only 12B active parameters suggests NVIDIA is optimising for agent workloads where inference cost matters more than raw size, and the open weights let teams self-host rather than depend on frontier API providers. Developers building document- or video-processing pipelines should evaluate it against Qwen-VL and other open multimodal models for agent deployment.
NVIDIA announced Nemotron 3.5 Super VL, an open-weight vision-language model for long-running AI agents. The model totals 120B parameters with 12B active, combining reasoning and tool use with text, image, document, and video understanding. It is designed to support agentic workflows that operate over extended sessions.
Meet NVIDIA Nemotron 3.5 Super VL Our new open model combines reasoning and tool use with text, image, document, and video understanding for long-running AI agents. 120B total parameters with 12B active 🧵 Your browser does not support the video tag. 🔗 View on Twitter 💬 22 🔄 50 ❤️ 308 👀 15393 📊 72 ⚡
