Running Local LLMs with Open WebUI
// 1 min read
Hey everyone. Hope this is useful to someone.
Lately I’ve been getting into AI models. Like a lot of you, I’ve been testing Ollama — it’s great for running powerful models locally, but typing ollama run in the terminal every time gets old.
Today I randomly found something on GitHub — Open WebUI, an open-source project that gives you a full ChatGPT-style frontend. I set it up, tested it with Ollama running Gemma 1B, and it looks and feels exactly like a local ChatGPT. Everything worked perfectly. The CPU heated up a bit (hit 81°C), but nothing to worry about with an i7 13700H — that’s what it’s built for.
Setting it up is straightforward, just follow the README.
Note: Docker and Python 3.12 are required.
GitHub: https://lnkd.in/e4-vipVF