nunchaku-ai/ComfyUI-nunchaku

ComfyUI Plugin of Nunchaku

54
/ 100
Established

Integrates SVDQuant-based 4-bit quantized models (FLUX, Qwen-Image, Z-Image) into ComfyUI's node workflow system, enabling efficient inference with asynchronous offloading to reduce VRAM usage. Supports multi-LoRA composition, ControlNet integration, and native ComfyUI nodes for streamlined model loading and generation without external dependencies.

2,800 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

2,800

Forks

151

Language

Python

License

Apache-2.0

Last pushed

Feb 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/nunchaku-ai/ComfyUI-nunchaku"

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