nunchaku-ai/nunchaku
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
SVDQuant decomposes weight outliers into separate low-rank components during 4-bit quantization, enabling aggressive quantization without quality loss across diffusion and image generation models. The engine provides native integration with ComfyUI and Hugging Face, supports dynamic LoRA composition and asynchronous CPU offloading to reduce VRAM requirements, and targets both consumer GPUs (20-series+) and enterprise hardware through optimized kernels for INT4 and NVFP4 precisions.
3,724 stars.
Stars
3,724
Forks
229
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nunchaku-ai/nunchaku"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
probabilists/azula
Diffusion models in PyTorch