Perplexity open-sources pplx-embed-v2 embedding models under MIT license
tomaarsen · x · 2026-10-08
Perplexity's research team released its second set of embedding models, pplx-embed-v2, on Hugging Face under an MIT license, spanning late-9b, late-0.6b and context-9b-preview variants. The 0.6B model starts from Qwen3.5-0.8B with its text tower pruned from 24 to 12 layers: 594M total parameters, with only 240M active for text encoding and 340M for images — the gap mostly comes from the large embedding table typical of small models. Install with:
bash
pip install "sentence-transformers>=6.0.0" "transformers>=5.4.0"
Both main variants passed 240 downloads within two days of release.
Related event: Perplexity Open-Sources Multimodal Embedding Models pplx-embed-v2-late(38 posts)→
More from Models
- ChatGPT Work mode vs Codex: same quota, far more tasks done per 5-hour window — sasik520 · 2026-10-08
- Claude Haiku 5.5 ships with huge jumps: OSWorld 15.7%→72.4%, beats GPT-6 Luna across the board — mark_k · 2026-10-08
- OpenAI on GPT-6 Intelligent UI: the hard part is knowing when to show it — btibor91 · 2026-10-08
- Burkov slams watermarking in paid LLM outputs: 'I paid for this text' — burkov · 2026-10-08
- 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