Install Ollama and Run Qwen3 4B Locally – AI Model Setup Guide

So, now we will learn how to install our AI model, that is Ollama. This is the most exciting part.

Instead of sending our data to a cloud service, we will run an AI model directly on our computer or laptop, that

I have already told to you. So, what we will do, we will use Ollama, which is a free tool that makes running

open-source AI models incredibly simple. So, think of Ollama as a platform that downloads and manages AI models for you.

So, once it is installed, you can run powerful language models with a single command.

So, how to install Ollama? Just go on this website, ollama.com/download, and download the installer, and

thereafter you can install it. Or on the Mac OS, you download the app from the Ollama download page, or use homebrew by

running brew install Ollama. So, this you have to use brew install Ollama. After you have installed the Ollama,

then you can download your first AI model. Remember it, first you have to go to the Ollama website and download it.

That is the framework. After the framework has been installed on your computer, then you can download

different AI models. So, now we are going to download our first AI model.

So, as I already told, an AI model is the brain of our assistant. There are many excellent open source

model available, but we will use Qwen 3.

Right? So, this is the model which we are going to use Qwen 3

because it provides a very good balance between a speed and quality on most modern laptops. So, if you will

download too heavy model, then your program will be very slow when you will run it because you don't have

the GPU or big server. So, you are running it on your desktop or laptop, your simple computer.

So, to download it, open the terminal and run this line. Open the terminal means command prompt

or power shell on Windows, and then you run this command Ollama pull Qwen 3 {colon} 4b. When you run this particular

command, what will happen is that it will start downloading this model on your

laptop or computer. This may take a few minutes because it has a

good size, maybe 4GB or 3GB, that kind of size it will have. So, it will take a little bit of time

depending upon your internet connection. Once the download completes, your model is installed on your computer, so you

would not need to download it again. So, that is the advantage. Only once you have to download it, now the AI model is

available on your local computer, and you can use that particular model. Next question is why Qwen

3? Throughout this course, we will use this lightweight open-source model that run

well on everyday hardware. So, we will be running our program on everyday hardware like all laptop, etc. So, we

cannot use very high AI model. If a newer, better model becomes widely available in the future, you can simply

replace the model name without changing the rest of the code. So, we will see that even if you want to use a paid

model on a server, only one or two information or your entire program has to be changed. That we call

configuration. Rest of the program will remain same. So, it is not like that you have to write the entire program from

the beginning. No, nothing like that. Only the model name has to be changed and the server information has to be

given. Only those information is changed, then your program, your earlier program is

still be running on that model. Now, the last step is we have to see whether our AI model is

working or running our laptop or desktop or not. So, let's make sure that everything is

installed correctly. Run the following command. Ollama run After a few seconds, you should see a

prompt where you can chat with the model. For example, hello. So, you will write hello, your model will reply,

"Hello, how can I help you today?" If your model has replied like this, that suggests that on your laptop or

desktop, the AI model has been downloaded successfully and it is working.

So, congratulations. You are now talking directly to an AI model running on your own computer.

After you have talked to it, you can type {slash} buy or press control C to exit from the terminal that we know or

understand. So, I think now you have done almost everything related with the

installation. You have Python, you have Visual Studio where you can write your Python program, and you have AI model

which you have downloaded. Now, your Python program will communicate with this AI model

to make different kind of programs or applications. I hope this is clear to you.

Thank you.