Open-Source LEANN Vector Index Shrinks RAG Storage by 97%
Researchers introduced LEANN, an open-source vector index that reduces a 60M-chunk RAG index from 201 GB to 6 GB using pruned graphs and GPU-batched re-embedding. While it maintains high recall with minimal storage, retrieval latency is significantly higher (2.48s vs 0.05s for HNSW), making it ideal for memory-constrained environments.
Full Report
▲ Marktechpost AI · 2026-10-27 21
▲ Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB
The key idea is simple: graph search only touches a few nodes per query. So LEANN stores a pruned graph plus small PQ codes. It re-embeds only the nodes on the search path, in GPU batches.
On a 76 GB Wikipedia corpus, LEANN needs 4 GB. HNSW needs 188 GB. Both hit 25.5% NQ accuracy at 90% recall. It is a trade-off though: retrieval takes 2.48 s vs 0.05 s for HNSW, and 44.80 s on HotpotQA on an M1 Ultra Mac.
MIT licensed, pip install leann, and it won Best Research Paper at MLSys 2026. Numbers are self-reported......
Full analysis:
