Skip to main content

GGUF Exporter Plugin

GGUF is a binary format optimized for quick loading and saving of models, making it highly efficient for inference and designed for use with GGML and other executors. Learn more about GGUF.

The GGUF Exporter Plugin allows you to export your model to the GGUF format with quantization. Follow the steps below to use the plugin.

Exporter GIF

Steps to Export​

  1. Download the Plugin:
    Navigate to the Plugins tab and download the GGUF Exporter Plugin.

  2. Switch to the Export Tab:
    After downloading, go to the Export tab.

  3. Select GGUF Exporter:
    Choose GGUF Exporter from the available export options.

  4. Configure Export Settings:
    a. Output Format: Configure the output format of the exporter. Supported values are q8_0, f16, or f32.

  5. Export the Model:
    Click Export. The plugin will process the request and display the exported model in the Foundation tab.

Explore the GGUF Exporter Plugin to simplify model quantization and export tasks!