Perplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA
Perplexity released pplx-embed-v2-late, a 0.6B edge embedder and a 9B model scoring 92.4% on MADQA.
Perplexity AI released pplx-embed-v2-late, an embedding family with a 0.6 billion parameter model for edge devices and a 9 billion parameter model for high-quality indexes. The larger model scores 92.4% on MADQA, while the weakest reported result is 61.2% on ViDoRe v3 Markdown. Both variants are MIT-licensed and available for self-hosting.
- 0.6B model targets edge devices; 9B model targets high-quality indexes.
- Best reported score is 92.4% on MADQA.
- Weakest reported score is 61.2% on ViDoRe v3 Markdown.
- Both variants are MIT-licensed and available to self-host.
- Vendors
- Perplexity
- Products
- pplx-embed-v2-late
- Organizations
- Perplexity AI
- AI models
- pplx-embed-v2-late
From the original article
Perplexity's pplx-embed-v2-late comes in 2 sizes: a 0. 6B model built to run on edge devices, and a 9B model for building high-quality indexes. Its best score is 92.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.