Firmamento-Technologies/TurboQuant

TurboQuant: Near-Optimal Vector Quantization for AI — Pure Python/NumPy implementation of Google Research's ICLR 2026 algorithm. 8x compression, 95%+ recall, zero preprocessing.

23
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 1 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

1

Forks

Language

Python

License

Apache-2.0

Last pushed

Mar 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Firmamento-Technologies/TurboQuant"

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