How to install and use ollama for hosting LLMs locally

Open source Large Language models are increasingly becoming viable alternatives to the closed source models that are available today. The first step towards understanding whether a model is a fit for your use case is to quickly get it up and running on your laptop or your machine. This article goes into a 5 minute setup guide for Ollama.

Ollama has made it easiest by far by providing a simple lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications.

With ollama you can run Llama 3.3, DeepSeek-R1, Qwen 3, Mistral, Gemma 3, and other models, locally.

1. Steps to install ollama in your machine:

Whether you are using mac , linux or windows operating system ollama supports all .

The below steps shown are done in macOS , but similar approach can be used in other operating system.

Visit https://ollama.com/.

• Click on the download button a zip file ollama-darwin.zip will be download shortly.

• Go to the downloads folder (or where the zip file is saved) , unzip the file you will see the ollama application extracted.

• Go ahead and move it to Applications

After successfully moving the ollama application to Application click on ollama. You will be prompted to install ollama.

• Make sure you have admin rights to you system as you will be prompted to validation that you are admin .

After the above steps are successful, you can now run any open source model in your machine.

Lets try it out!!

• Open a terminal and type.

 ollama run <model name>

After successful run (might defer based on model):

Congratulations !! you have an AI running in your machine!

Example:

Tip !

# use below command to exit 

/bye

References:

Github : https://github.com/ollama/ollama

Ollama : https://ollama.com/