Quantized GGUF version of Bernini-R for ComfyUI.

Original model link: https://huggingface.co/ByteDance/Bernini-R

ComfyUI-Bernini custom nodes: https://github.com/AIMixer/ComfyUI-Bernini

bilibili: https://www.bilibili.com/video/BV1GMjP6gEDp/

Downloads last month
94
GGUF
Model size
14B params
Architecture
wan
Hardware compatibility
Log In to add your hardware

4-bit

5-bit

6-bit

8-bit

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