Lynx gguf models
#14
by dozaler - opened
Can you make gguf conversion of lynx models? Particularly the Wan2_1_T2V_14B_Lynx_lite_fp16.safetensors one? Can't load this with main diffusion model ggufs. If I use safetensors diffusion models I run out of vram. Tried to convert it with a guide myself but llama.cpp threw an error saying it doesn't recognize the model architecture.
Edit: Found gguf conversions: https://huggingface.co/patientxtr/Wan2_1-T2V-14B-Lynx-GGUF/tree/main