Phr00t

/

WAN2.2-14B-Rapid-AllInOne

like 1.48k

Looks like someone has been making them here: https://civitai.com/models/1855105/rapid-wan-22-i2v-gguf

Can someone make quantized gguf or tell me how to do it? I have the hardware for it (128GB RAM) (Nvidia RTX 4060 TI 16GB VRAM).

City96 has instruction how to quant, maybe it helps you in future - https://github.com/city96/ComfyUI-GGUF/tree/main/tools Also there is something for ComfyUi quantizer: https://github.com/lum3on/ComfyUI-ModelQuantizer

Looks like someone has been making them here: https://civitai.com/models/1855105/rapid-wan-22-i2v-gguf

Thank you :)

Can someone make quantized gguf or tell me how to do it? I have the hardware for it (128GB RAM) (Nvidia RTX 4060 TI 16GB VRAM).

City96 has instruction how to quant, maybe it helps you in future - https://github.com/city96/ComfyUI-GGUF/tree/main/tools Also there is something for ComfyUi quantizer: https://github.com/lum3on/ComfyUI-ModelQuantizer

Thank you :)