outmatic/TurboQuant

High-performance .NET implementation of Google's TurboQuant algorithm (ICLR 2026). Near-optimal vector quantization: compress embeddings to 2-4 bits with cosine > 0.995.

22
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

C#

License

MIT

Category

utility

Last pushed

Apr 03, 2026

Commits (30d)

0

GitHub
Utility · 7 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/outmatic/TurboQuant"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

vcal-project/vcal-core

VCAL Core — high-performance semantic cache and vector cache library for LLM applications.

40

gorajing/zuhn

Personal knowledge operating system — ingests content, extracts insights via Claude, and stores...

22

stffns/snapvec

Fast compressed ANN search via randomized Hadamard transform + Lloyd-Max quantization. Pure NumPy.

14

stffns/hadamax

Fast compressed ANN search via randomized Hadamard transform and optimal Gaussian scalar...

14

ctx-0/embed-engine

resumable batch image embedding pipeline

14

Explore Embedding Tools

All categories Trending Embeddings directory Insights