Perplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA

Perplexity AI has released two open-source embedding models, pplx-embed-v2-late, available in 0.6B and 9B parameter sizes. The smaller version is designed for edge computing, while the 9B model is intended for high-quality indexing tasks and achieved a 92.4% score on the MADQA benchmark. Both models are released under an MIT license, allowing developers to self-host them for custom search and retrieval applications.