Local GGUF model

We support custom GGUF models with your local GGUF files. You can create any number of local GGUF model and delete GGUF models. RecurseChat is powered by llama.cpp under the hood. The app should work with most GGUF models that llama.cpp supports. You can create a new local GGUF model by linking your GGUF files.

To create a new local GGUF model, follow these steps:

• Go to Model page by clicking the “Model” button on the bottom left toolbar.
• Click the “New Model” button, and click the “New Local GGUF Model” button.
• Click “Link GGUF” button and select your GGUF files from file system.
• Click “Create” button.

Tips

Popular places to find GGUF models:

• TheBloke’s Models on Hugging Face
• GGUF Model Hub