---
title: "LEANN vector index shrinks 60M-chunk RAG index from 201 GB to 6 GB"
url: https://www.parallelquant.com/posts/leann-vector-index-shrinks-60m-chunk-rag-index-from-201-gb-to-6-gb-0cb3de
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/27/leann-vector-index-mlsys-2026/
published: 2026-10-27T21:54:37.000Z
topics: ["research", "open source"]
publisher: "Parallel Quant"
---

# LEANN vector index shrinks 60M-chunk RAG index from 201 GB to 6 GB

*2026-10-27 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/27/leann-vector-index-mlsys-2026/)*

UC Berkeley's open-source LEANN stores a pruned graph and recomputes embeddings at query time. It matches HNSW (a standard graph index) accuracy at 90% recall using 4 GB instead of 188 GB. The cost is search latency measured in seconds.

**Why it matters:** Storage is a major cost of local and personal-scale RAG, so trading compute for ~30x less disk makes on-device retrieval over large corpora practical. The seconds-level latency limits it to non-interactive or small-scale uses, but it reflects a broader shift of recomputing instead of storing as GPUs get cheaper than memory.

**Topics:** research, open source

---
Read the original: https://www.marktechpost.com/2026/10/27/leann-vector-index-mlsys-2026/
Canonical: https://www.parallelquant.com/posts/leann-vector-index-shrinks-60m-chunk-rag-index-from-201-gb-to-6-gb-0cb3de
Published by Parallel Quant — https://www.parallelquant.com