A ComfyUI Workflow with GGUF Loader nodes.
GGUF quantization's usually help larger models run on less VRAM
Get OmniNodes on the ComfyUI Manager or here: https://github.com/TensorVizion/OmniNodes
Other Generative AI Resources:
Description
ComfyUI Workflow
Deploy on Runpod: https://runpod.io?ref=1jcw9158