Wan_2.2_ComfyUI_Repackaged IQ4_XS

llama-cli -hf calcuis/wan2-gguf:IQ4_XS

Downloads and runs in one step, resolving the quantization by name.

hf download calcuis/wan2-gguf --include "wan2.2-animate-14b-iq4_xs.gguf"

This quantization is split across 7 files totalling 58.65 GiB. You need every part — the first is not a smaller version of the model.

• wan2.2-animate-14b-iq4_xs.gguf
• wan2.2-i2v-14b-high-noise-iq4_xs.gguf
• wan2.2-i2v-14b-low-noise-iq4_xs.gguf
• wan2.2-s2v-14b-fp32-iq4_xs.gguf
• wan2.2-t2v-14b-high-noise-iq4_xs.gguf
• wan2.2-t2v-14b-low-noise-iq4_xs.gguf
• wan2.2-ti2v-5b-fp32-iq4_xs.gguf

Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.