Pre-check: open Task Manager → Performance to see RAM and GPU. Then run this in Command Prompt to see GPU name, driver version and VRAM. Also check free disk space.
nvidia-smi
Do you see your GPU name and "Driver Version"?
First install Ollama (see the Ollama guide) and run one model.
Pre-check: see your RAM (Task Manager / About This Mac / free -h). Small tools run without a GPU — just slower.
Know how much RAM you have?
Same as your OS tab. Without a GPU keep 1B–3B models in Ollama.
Sizes are approximate and can change on the official page.
Errors & fixes
"No models available" in Open WebUI
Ollama is not running or has no models. Run ollama run llama3.2:3b and refresh.
pip error about Python version
Open WebUI needs Python 3.12. Create the venv with py -3.12.
Port 8080 already in use
Another app uses 8080. Run open-webui serve --port 8081.
"python is not recognized" / "command not found: python"
Python is missing or not on PATH. Install from python.org and tick "Add python.exe to PATH" on the first installer screen, then open a new terminal. On Mac/Linux use python3.
Open WebUI: Tools (give the model abilities), Functions (Pipes = new model providers, Filters, Actions), MCP via mcpo or native external tools; community site openwebui.com.
Stars, license and last update come from GitHub (17 Nov 2026). Commands are copied from official docs and are not tested on a real machine yet. Access tags are our summary — always check the source. Skills for every AI →