Perplexity open-sources pplx-embed-v2-late: 9B and 0.6B multimodal embeddings
CShorten30 · x · 2026-10-08
Perplexity has open-sourced pplx-embed-v2-late, a pair of late-interaction multi-vector embedding models (9B and 0.6B) sharing one embedding space for text and images. The 9B model indexes multimodal data while the 0.6B model queries on device. It retrieves PDF pages without OCR and scores 92.4% on MADQA and 64% on BrowseComp+. Weights are on Hugging Face.
More from Models
- Epoch's InnovationEval: AI agents still far from producing real research innovations — Afinetheorem · 2026-10-08
- 113 decision models in 3 weeks: 70 built on Qwen, sub-cent per call — jonathanmalkin · 2026-10-08
- User reports Haiku 5.5 is a major workflow upgrade in screenshot post — Sorcerer12345 · 2026-10-08
- OpenRouter launches Decision Model Rankings, with typesafeai leading all categories — gaganghotra_ · 2026-10-08
- OpenAI launches Intelligent UI: ChatGPT now answers with fully interactive interfaces — gdb · 2026-10-08
- Claude Haiku 5.5 Beats GPT-6 Luna on Every Benchmark but Costs 5x Past 100k Tokens — daniel_mac8 · 2026-10-08