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

UC Berkeley researchers released LEANN, an open-source vector index that stores a pruned graph and recomputes embeddings at query time, shrinking a 60-million-chunk RAG index from 201 GB to 6 GB. LEANN matches HNSW accuracy at 90% recall using 4 GB instead of 188 GB, at the cost of seconds-level search latency.

UC Berkeley’s LEANN vector index stores a pruned graph and recomputes embeddings at query time. It matches HNSW accuracy at 90% recall using 4 GB instead of 188 GB, at the cost of seconds-level search. The post Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB https://www.marktechpost.com/2026/10/27/leann-vector-index-mlsys-2026/ appeared first on MarkTechPost https://www.marktechpost.com .