Announcement
Nvidia's Nemotron 3.5 Super VL goes live on Together AI
Nvidia says the open model combines reasoning and tool use with text, image, document and video understanding.
TLDR
Together AI says Nvidia's open-weight multimodal model is now available on its platform. Nvidia describes it as designed for long-running agents that work with text, images, documents and video, with 120 billion total parameters and 12 billion active. Nvidia says combining text and visual understanding reduces the need to pass context between separate models.
Combined views
664.8K
44 Sources, first seen ago
