Deep dive
The full breakdown - performance, comparisons, and setup
faiss
faiss is a local-AI tool - A library for efficient similarity search and clustering of dense vectors.
Overview
Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning. Faiss is written in C++ with complete wrappers for Python/numpy. Some of the most useful algorithms are implemented on the GPU. It is developed primarily at Meta's Fundamental AI Research group.
See CHANGELOG.md for detailed information about latest features.
Faiss contains several methods for similarity search. It assumes that the instances are represented as vectors and are identified by an integer, and that the vectors can be compared with L2 (Euclidean) distances or dot products. Vectors that are similar to a query vector are those that have the lowest L2 distance or the highest dot product with the query vector. It also supports cosine similarity, since this is a dot product on normalized vectors.
faiss is open-source, written primarily in C++, with 41,124 GitHub stars under the MIT license. The latest release is v1.15.1 (2026-09-16).
Key capabilities
From the project's documentation:
- memory used per index vector
- need for external data for unsupervised training
- the doxygen documentation gives per-class information extracted from code comments
- Hervé Jégou initiated the Faiss project and wrote its first implementation
- Matthijs Douze implemented most of the CPU Faiss
- Jeff Johnson implemented all of the GPU Faiss
How it fits a local-AI stack
faiss runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related local-AI tools in the directory:
Sources
- Source code & docs: facebookresearch/faiss
- Official website: https://faiss.ai
Stats from GitHub, 2026-10-10.
Frequently asked
Quick answers to common questions
What is faiss?
faiss is a other tool for local AI workloads. A library for efficient similarity search and clustering of dense vectors.
Is faiss free and open source?
Yes, faiss has 41,124 GitHub stars and is licensed under MIT. You can self-host it for free on .
What hardware do I need for faiss?
The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. faiss has 41,124 GitHub stars and an active community.
Does faiss support GPU acceleration?
faiss's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.
What are the best alternatives to faiss?
Popular alternatives include other other tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.
How much does faiss cost?
faiss is free-open-source. It is completely free and open source to self-host.
Pairs well with
Complementary tools, models, and hardware