This is a direct GGUF conversion of alibaba-pai/Wan2.1-Fun-14B-InP

The model files can be used with the ComfyUI-GGUF custom node.

Place model files in ComfyUI/models/unet - see the GitHub readme for further install instructions.

The VAE and additional files can be downloaded from Comfy-Org/Wan_2.1_ComfyUI_repackaged - they are the same as the base Wan2.1 model.

Please refer to this chart for a basic overview of quantization types.

GGUF

Model size

16.4B params

Architecture

wan

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for city96/Wan2.1-Fun-14B-InP-gguf

Base model

Quantized

(1)

this model

Collection including city96/Wan2.1-Fun-14B-InP-gguf