ComfyUI-GGUF allows running it in much lower bits per weight variable bitrate quants on low-end GPUs. For further VRAM savings, a node to load a quantized version of the T5 text encoder is also included.

Download flux1-dev GGUF models:

https://huggingface.co/city96/FLUX.1-dev-gguf/tree/main

Download flux1-schnell GGUF models:

https://huggingface.co/city96/FLUX.1-schnell-gguf/tree/main

Download t5_v1.1-xxl GGUF models:

https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/tree/main

**************************************

Click on below link for video tutorials:

https://www.youtube.com/@CgTopTips/videos