# nunchux-ai/nunchaku — RepoVerse

\[ICLR2025 Spotlight\] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

URL: https://repoverse.app/cards/884123664

[Repository source](https://github.com/nunchux-ai/nunchaku)

## Card snapshot

- Edition: Genesis
- Rarity: common
- Finish: Base
- Attack: 4324
- Defense: 2581
- GitHub stars: 3960
- GitHub forks: 285
- Language: Python
- Category: Python Ecosystem
- Snapshot date: 2026-10-22

These repository statistics and game attributes belong to this dated card snapshot. They are not a current assessment of software quality.

This page describes the repository card, without a holder or individual copy record.

- [Rules](https://repoverse.app/rules.md)
- [Explore](https://repoverse.app/explore)