Meet Turbovec: A Rust Vector Index with Python Bindings, and Built on Google’s TurboQuant Algorithm

turbovec, a new open-source vector index, was released with Rust core code and Python bindings for easy integration.

It uses Google Research’s TurboQuant for zero-training quantization, sharply compressing embeddings to reduce RAM needs.

Benchmarks report recall competitive with FAISS, with faster search on some ARM and x86 systems, including Apple M3 Max and Intel Xeon Platinum 8481C.

The project could lower infrastructure costs for large embedding indexes while keeping vector search performance strong for RAG and similar workloads.