Qdrant Generates 32.8M Embeddings in 35 Minutes With Static Embedding Models

qdrant_engine · x · 2026-11-18

Qdrant partnered with Minish Lab on an article about static embeddings: Fastembed now integrates Minish's potion static embedding models, generating 32.8M embeddings in 35 minutes. The diagram shows the mechanism — tokenize, look up per-token rows, mean pool, L2-normalize into 256-dim unit vectors, with no transformer forward pass. The piece covers how static embeddings work, the optimizations added to Fastembed to speed them up, and the retrieval-quality tradeoffs versus contextual embeddings.

Related event: Qdrant and Minish Generate 32.8M Vectors in 35 Minutes with Static Embeddings(2 posts)→

Original post →

More from Infra

Infra channel →