Source: Faiss indexes (Faiss wiki)
Reference table of Faiss index types with their parameters, bytes per vector and whether search is exhaustive.
Contents
- What: reference documentation page on the Faiss GitHub wiki
- Author: Meta FAIR / Faiss maintainers
- Date: living document (read 2026-11-14)
- Original: github.com/facebookresearch/faiss/wiki/Faiss-indexes
Summary
A cheat sheet of the main Faiss index classes, which are the reference implementations of the index families most vector databases reuse. Its value is the memory column: it makes explicit what each family costs per vector.
Key claims
- Flat (L2 or inner product): exact, 4*d bytes per vector. Cosine is inner product on normalized vectors.
- HNSWFlat: parameters M, efConstruction, efSearch; memory is the raw vector plus graph links; vectors cannot be removed.
- IVFFlat:
nlistand query-timenprobe; 4*d + 8 bytes (the 8 bytes store the ID). - Scalar quantizer SQ8: d bytes per vector (4x smaller than float32); SQ4 and fp16 variants exist.
- PQ: M sub-quantizers of
nbitseach, ceil(M*nbits/8) bytes; d must be a multiple of M. - IVFPQ: PQ code plus 8 bytes, non-exhaustive; typical code sizes are 4 to 64 bytes.
- Suggested
nlistis about C*sqrt(n) with C around 10.