Skip to content
 
 

Repository files navigation

ComfyUI-GGUF

GGUF Quantization support for native ComfyUI models including the custom Q8_CR.

Note

This is a fork of the original nodes, updated to support loading Ideogram 4 GGUFs and Krea 2 GGUFs. To use this maintained fork, clone https://github.com/molbal/ComfyUI-GGUF.

While quantization was previously unfeasible for regular UNET models (conv2d), transformer/DiT models such as flux are less affected by quantization. This allows running them in lower bits per weight variable bitrate quants on GPUs with less VRAM.

More details on how to use it, pre-converted models, and sample workflows are here: Documentation

For technical details on the custom Q8_CR and Q4_CR formats , memory-mapped loading, please see ARCHITECTURE.md.

Installation

Important

Make sure your ComfyUI is on v0.27.0 or later.

To install the custom node normally, git clone this repository into your custom nodes folder (ComfyUI/custom_nodes) and restart ComfyUI.

git clone https://github.com/molbal/ComfyUI-GGUF

Usage

Simply use the GGUF Unet loader found under the bootleg category. Place the .gguf model files in your ComfyUI/models/unet folder.

Pre-quantized models (🍴 icon on ones added by this fork):

[!IMPORTANT] > Please note, that this fork does not support _K quants on diffusion models, only on text encoders. They may or may not load, but inference speed may be very slow. There may be other forks, or other custom nodes with better support for these quantization types.

Initial support for quantizing T5 has also been added recently, these can be used using the various *CLIPLoader (gguf) nodes which can be used inplace of the regular ones. For the CLIP model, use whatever model you were using before for CLIP. The loader can handle both types of files - gguf and regular safetensors/bin.

Converting Models (Krea 2, Ideogram 4, MiniMax H3, MiniMax Music 3)

This node pack includes a GGUF converter. It has 3 possible interfaces that you can use:

  • a python file you can call directly
  • a web interface
  • a custom node

Each option is documented here: Quantizing models

Supported Conversion Formats

Format Storage / execution Recommended use
F16 FP16 GGUF Maximum compatibility with half-precision storage.
BF16 BF16 GGUF Preserve BF16 source models where the target supports BF16.
Q8_0 Standard GGML 8-bit Excellent general-quality 8-bit GGUF.
Q5_1 Standard GGML 5-bit Lower storage with a quality-oriented 5-bit format.
Q5_0 Standard GGML 5-bit Lower storage alternative to Q5_1.
Q4_1 Standard GGML 4-bit Smaller files when VRAM or RAM is constrained.
Q4_0 Standard GGML 4-bit Smallest supported format for constrained setups.
Q8_CR Per-row INT8 ConvRot Maintainer recommendation for NVIDIA RTX 30-series systems.
Q4_CR Experimental INT4 ConvRot Maintainer recommendation for NVIDIA RTX 30-series systems.

Releases

Packages

Contributors

Languages