Perplexity Releases pplx-embed-v2-context-9b-preview, Matches Voyage With 8x Less Storage

perplexity_ai · x · 2026-10-01

Perplexity launched pplx-embed-v2-context-9b-preview on Hugging Face. It posts the highest average nDCG@10 on ConTEB among tested models (not on every task) and beats voyage-context-4 on chunk retrieval while using 8x less storage per vector: 1 KB (1024 dims, int8) vs 8 KB (2048, float32).

Related event: Perplexity releases pplx-embed-v2-context-9b-preview, tops ConTEB embedding benchmark(5 posts)→

Original post →

More from Models

Models channel →