Ollama — run open-source LLMs locally to learn how they work

Okay let's break into AI one really important step is being able to run models locally and researching how they work. The first thing we're going to do is we're going to go to olama.com so when you bring up the site over here to the right you've got download over here to the left I want to show you this first before I forget which is models these are the different models that you can download directly from olama run them locally and then do some research build apis do all sorts of really cool things with them so the first thing we want to do is we want to go to download it is going to detect what operating system you're on you're going to click I'm clicking macOS it's going to download it go to the zip file unzip it install it now once you have that done the next thing you're going to do is you're going to go to terminal you can type in olama run and then I want to run Yema3 it is going to bring it up automatically it takes a couple seconds the first time you do it and when you download it for the first time it can take maybe five or ten minutes depending on your internet speed but I've got it locally let's do something so uh tell me how to cook a strip steak and notice within a second it is bringing back information so this is how you can run a large language model locally it is not going out to the internet it is not sharing your information now we're going to install a couple more tools but the next thing we're going to install is open web UI what I like about that is it…