Firmamento-Technologies/TurboQuant

Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement

20
Stars
3
Forks
19.8
Radar Score
Stable
Momentum

Scoring Breakdown

Impact11.4
Velocity20.9
Health31.7

Growth Metrics

7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python

Why it ranks

Modest but positive momentum.

LLM Frameworks · quantizationTop 97% globally
View on GitHub