Hugging Face has announced the release of Granite Embedding Multilingual R2, an open-source multilingual embedding model available under the Apache 2.0 license. The model supports 32,000 token context length and is designed to deliver retrieval quality comparable to much larger models while remaining under 100 million parameters. This approach makes it suitable for deployment in resource-constrained environments while maintaining strong performance across multiple languages. The release targets developers and organizations seeking efficient embedding solutions for semantic search, information retrieval, and vector database applications. By combining multilingual capabilities with extended context windows in a compact model size, Granite Embedding R2 aims to provide a practical alternative to larger proprietary embedding models. The Apache 2.0 license enables unrestricted commercial and research use.