Nemotron Multimodal Embedding NIM

NVIDIA NeMo Retriever Multimodal Embedding NIM provides optimized inference for the Nemotron 3.5 Embed model family. It converts text, document-page images, or combined image-text content into dense vector embeddings, enabling text queries to retrieve semantically relevant information from documents containing text, tables, charts, and infographics.

The NIM supports Nemotron 3.5 Embed 1B in BF16 and NVFP4 precision and Nemotron 3.5 Embed 8B in BF16 precision. These models are optimized for multilingual and multimodal question-answering retrieval, with evaluation coverage spanning 34 languages for text retrieval and 18 languages for image retrieval.

Use Multimodal Embedding NIM to build semantic search, multimodal Retrieval-Augmented Generation (RAG), and agentic RAG applications over large document collections. Built on the NVIDIA software platform and accelerated with CUDA, the NIM provides production-ready GPU inference through industry-standard APIs.

Getting started with the NIM

Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NIM Container page for release documentation, deployment guides and more.

Security Vulnerabilities in Open Source Packages

Please review the Security Scanning tab on NGC to view the latest security scan results.

For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

Get Help

Enterprise Support

Get access to knowledge base articles and support cases or submit a ticket.

NVIDIA Developer Community Forum

Get access to community knowledge base articles and support cases (https://forums.developer.nvidia.com/)

Governing Terms

The NIM container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for AI Products.

You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.