Did UC Berkeley release LEANN, an open-source vector index that shrinks a 60M-chunk RAG index from about 201 GB to 6 GB while matching HNSW accuracy?

UnconfirmedLast checked
UC BerkeleyFirst seen

Verdict

MarkTechPost summarizes the LEANN paper/repo and MLSys 2026 Best Research Paper award; primary paper numbers not re-run here.

Evidence timeline · 1 source · newest first
  1. Unconfirmed

    MarkTechPost covers UC Berkeley Sky Computing Lab’s LEANN, an MIT-licensed vector index that stores a pruned graph and recomputes embeddings at query time, reporting a 60M-chunk Wikipedia index cut from 201 GB to 6 GB while matching HNSW accuracy at 90% recall; the paper won Best Research Paper at MLSys 2026.

    Source: MarkTechPost
Quick answers
Is UC Berkeley LEANN vector index out yet?
No. UC Berkeley has not announced it as of Oct 28.
When is UC Berkeley LEANN vector index expected?
No official release date as of Oct 28.
How we label rumors
Unconfirmed
Circulating with at least one public source we can link to; no official confirmation.
Reported
Reported by a news outlet; not confirmed by the company.
Confirmed
Confirmed by the company or another official source.
Debunked
Denied by the company, retracted by the original source, or shown to be false by the evidence.

We record what sources show, with dates. We don't predict or score how likely a rumor is.

DailyCitedRSSAboutPrivacy