A vector index built on TurboQuant, written in Rust with Python bindings

A 10 million document corpus takes 31 GB of RAM as float32. turbovec fits it in 4 GB - and searches it faster than FAISS.

turbovec is a Rust vector index with Python bindings, built on Google Research's TurboQuant algorithm — a data-oblivious quantizer with near-optimal distortion and no separate training phase.

  • Online ingest. Add vectors, they're indexed — no train step, no parameter tuning, no rebuilds as the corpus grows.

  • Fast SIMD search. Hand-written NEON (ARM) and AVX-512BW (x86) kernels beat FAISS IndexPQFastScan by 10–19% on ARM; on x86 they win the 4-bit configs and trail by a few percent on 2-bit.

  • Filter at search time. Pass an id allowlist (or a slot bitmask) to search() and the kernel honours it directly. You always get up to k results from the allowed set — no over-fetching, no recall hit on selective filters.

  • Pure local. No managed service, no data leaving your machine or VPC. Pair with any open-source embedding model for a fully air-gapped RAG stack.

Building RAG where privacy, memory, or latency matters?