Qdrant embeds 32.8M passages in 35 minutes on a laptop CPU with static embeddings

qdrant_engine · x · 2026-11-18

Qdrant and Minish detail how static embedding models (potion series, model2vec) — simple token-vector lookup tables with mean pooling, no transformer layers — let Fastembed embed 32.9 million passages in 35 minutes on a laptop CPU, versus 53 days for a transformer model. The article covers how static embeddings work, the optimizations added to Fastembed, and the retrieval-quality tradeoff of skipping inter-token interactions.

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

Original post →

More from Infra

Infra channel →