# LEANN open-source vector index cuts a 60M-chunk RAG index from 201 GB to 6 GB

> Original title: Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB

- Source: MarkTechPost
- Published: 2026-10-27T21:54:37.000Z
- Bad Influence: https://badinfluence.news/items/uv8i6slrbrvflw7gdlviir4f2
- Original: https://www.marktechpost.com/2026/10/27/leann-vector-index-mlsys-2026/

## Summary

UC Berkeley's Sky Computing Lab released LEANN, an open-source vector index that stores a pruned graph and recomputes embeddings at query time instead of saving them. The repo benchmark shows a 60 million chunk Wikipedia index shrinking from 201 GB to 6 GB, with retrieval taking seconds rather than milliseconds on the tested hardware.