Running DeepSeek-R1 and Llama 3.3 Locally with Ollama and Open WebUI

Run state-of-the-art open reasoning models on your local hardware with full chat history, document upload, and zero cloud API charges.

1. Launch Ollama Engine

# Run DeepSeek-R1 14B or 8B quantized for your RAM capacity
ollama run deepseek-r1:14b

2. Connect Open WebUI in Docker

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data --name open-webui \
  --restart always ghcr.io/open-webui/open-webui:main

Navigate to `http://localhost:3000` to interact with your local models in a ChatGPT-grade user interface.