Ctrl+K
Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices
Multimodal question-answer retrieval representing user queries as text and documents as images.
1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
Cutting-edge vision-language model exceling in retrieving text and metadata from images.
Nemotron Nano 12B v2 VL enables multi-image and video understanding, along with visual Q&A and summarization capabilities.
Record-setting accuracy and performance for Mandarin Taiwanese English transcriptions.
