How to get oobabooga/text-generation-webui running on Windows or Linux

Published On - March 5, 2025

ivan Blogging

How to Get Oobabooga/Text-Generation-WebUI Running on Windows or Linux

Oobabooga’s Text-Generation-WebUI is a powerful tool for running and interacting with language models on personal computers. It provides a convenient interface for loading and managing different text-generation models without requiring advanced command-line experience. This guide will walk through the installation and setup process for both Windows and Linux users.

Prerequisites

Before installing Text-Generation-WebUI, make sure your system meets the following requirements:

  • A modern CPU (preferably with AVX2 support)
  • At least 8GB of RAM (16GB or more recommended for larger models)
  • A compatible GPU (NVIDIA GPUs provide the best performance with CUDA)
  • Python 3.10 or newer installed
  • Git installed

Installation on Windows

  1. Download and install Git if it’s not already installed.
  2. Download and install Python 3.10+.
  3. Open a command prompt and clone the repository:
    git clone https://github.com/oobabooga/text-generation-webui.git
  4. Navigate into the project folder:
    cd text-generation-webui
  5. Run the setup script:
    python -m venv venv
    venv\Scripts\activate
    pip install -r requirements.txt
  6. Start the web UI:
    python server.py

Once the server starts, open a web browser and go to http://localhost:5000 to access the interface.

Installation on Linux

  1. Ensure that Git and Python 3.10+ are installed:
    sudo apt update && sudo apt install -y git python3 python3-venv
  2. Clone the Text-Generation-WebUI repository:
    git clone https://github.com/oobabooga/text-generation-webui.git
  3. Navigate into the project directory:
    cd text-generation-webui
  4. Set up a virtual environment and install dependencies:
    python3 -m venv venv
    source venv/bin/activate
    pip install -r requirements.txt
  5. Start the server:
    python server.py

Similar to Windows, open a browser and navigate to http://localhost:5000 to start using the UI.

Downloading and Using Models

Once Text-Generation-WebUI is running, users can download and interact with different models. The process involves:

  1. Clicking on the “Model” tab in the web interface.
  2. Choosing a model from Hugging Face or another source.
  3. Downloading and loading the selected model.
  4. Inputting text prompts to generate responses.

For better results, it is recommended to experiment with different model parameters, such as temperature and top-k sampling, which control how the AI generates text.

Troubleshooting Common Issues

Some users may experience issues while setting up the application. Here are some common problems and their solutions:

  • Module not found: Ensure the virtual environment is activated before running the server.
  • Python version mismatch: Make sure Python 3.10 or newer is installed.
  • CUDA-related errors: If using an NVIDIA GPU, confirm that CUDA and cuDNN are correctly installed.

FAQs

Can I use this without a GPU?
Yes, but performance will be significantly slower. Using a GPU with CUDA support is recommended.
How do I download additional models?
Use the “Model” tab in the UI to browse and download models from Hugging Face.
Can I run this on macOS?
Yes, the setup is similar to Linux but may require additional tweaks for compatibility.
How do I update the web UI?
Navigate to the project folder and run:
git pull
pip install -r requirements.txt
Where can I get help?
Check the official GitHub repository for issues and discussions.