ComfyUI-GGUF

GGUF Quantization support for native ComfyUI models This is currently very much WIP. These custom nodes provide support for model files stored in the GGUF format popularized by llama.cpp. While quantization wasn't feasible for regular UNET models (conv2d), transformer/DiT models such as flux seem less affected by quantization. This allows running it in much lower bits per weight variable bitrate quants on low-end GPUs.

2047
Stars
city96
Author
5/9/2025
Last Update
847
Days

Category

model

Description

GGUF Quantization support for native ComfyUI models This is currently very much WIP. These custom nodes provide support for model files stored in the GGUF format popularized by llama.cpp. While quantization wasn't feasible for regular UNET models (conv2d), transformer/DiT models such as flux seem less affected by quantization. This allows running it in much lower bits per weight variable bitrate quants on low-end GPUs.

Technical Information

Install Type:git-clone
Node ID:23016

Related Nodes

Discover more nodes in the same category or by the same author.

View all model nodes →