HOW to bring Artificial Intelligence to your Raspberry Pi | Ollama Large Language Models

In this video we show you how to run Large Language Models locally on your Raspberry Pi. You need a Raspberry Pi 4B or 5. 8Gb of ram is recommended, but we did it with 4Gb on our Pi 5. It is very easy to set it up and make an AI chatbot from your Pi. There are a lot of models to choose from, so you can play around for a while ;). You really get amazing results when you start a conversation with the chatbot or for example let the model generate code.
Have fun! And if you liked the project, please consider buying us a cup of coffee.🧡
www.buymeacoff...
You can find all commands we use in this video on our GitHub: github.com/Blo...
Ollama website:
ollama.com/
Raspberry Pi Imager:
www.raspberryp...
Putty:
www.chiark.gre...
Bloxy Labs is now present on X! Follow us to see what we are doing and share your own ideas with us!!
/ bloxy_labs

[@titicruz1991]

hey! First, Great Video!
Is it possible to create like an API or something to call the AI bot from another APP? For example, having the AI Bot listening to requests and another APP on another pc requesting the AI. Would be nice to have a video about it :)

[@BloxyLabs]

Thanks!! I'm planning to do something with a gui. But if you are interested in a API, check this: github.com/ollama/ollama/blob/main/docs/api.md

[@CC-zr6fp]

Was wondering if I missed a step. When trying ollama run llama3 I am met with "no such file or directory"

[@emirsatlms8059]

Thank you for your informative video, I would like to ask is it possible to shape the model such as openai playground? and do you think pi zero can run this model?

[@BloxyLabs]

Unfortunately it doesn't work on a Pi Zero. I think you need at least a Pi 5 to make it all work properly. I have no experience yet with working with multiple models in an AI playground, but this may be something for the near future ;)