nunchaku
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Run a high-performance engine for 4-bit neural networks to enhance your AI model's capabilities and performance.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
nunchaku has 3.9k stars on GitHub. It has been forked 265 times. nunchaku is written mainly in Python. It has been in active development since 2024. nunchaku is available under the Apache-2.0 license. Its main topics are comfyui, diffusion-models, flux, genai.
What is nunchaku?
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Is nunchaku open source?
nunchaku is an open-source project. It is released under the Apache-2.0 license.
Is nunchaku free?
Yes. nunchaku is free and open source — you can use, modify and self-host it.
What license does nunchaku use?
nunchaku is available under the Apache-2.0 license.
What language is nunchaku written in?
nunchaku is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/nunchaku-ai-nunchaku.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.