Run AI Locally on a Raspberry Pi with Ollama
In this video, I go through the steps of setting up Ollama on the Raspberry Pi. Using Ollama, you can install and use a range of large language models (LLM) on your Pi.
Tutorial: https://pimylifeup.com/raspberry-pi-o...
I used the following pieces of equipment in this tutorial.
We may earn an affiliate commission if you buy through our Amazon links.
Raspberry Pi: https://amzn.to/3WUT8Ij
Micro SD Card: https://amzn.to/3US0ZUz
Ethernet Cable: https://amzn.to/3K8BcT7
Unlike models such as GPT, you can run all the available models via Ollama locally on your device. Making it a great choice if you are concerned about privacy.
Using the Raspberry Pi is a great way to use some basic local AI without investing in expensive equipment.
Running large language models is very resource-intensive, so you must be careful of the models you utilize. Smaller models such as PHI3 or TinyLlama will perform better than something like Llama3.
I hope this tutorial has helped you get Ollama running on your Raspberry Pi and you have tried out a few different AI models.