Install and Run NVIDIA Nemotron 3 Nano 30B on Linux Ubuntu

In this tutorial, we explain how to install and run locally the NVIDIA Nemotron 3 Nano 30B model on a Linux Ubuntu computer. The YouTube tutorial is given below.

The first step is to install Ollama and download the model. To install Ollama, first open a terminal and type

sudo apt update && sudo apt upgrade
sudo apt install curl
curl -fsSL https://ollama.com/install.sh | sh

Then, to download and install the model, open a terminal and type:

ollama run nemotron-3-nano

This will download and install the model. It will take 5-10 minutes to install the model. After the model is installed it will be automatically executed. You can exit the Ollama model terminal by pressing CTRL+Z.

The next step is to install Open WebUI in order to run the model inside of a GUI. To do that, open a terminal and type

cd ~ 
mkdir testWebUI
cd testWebUI

which Python
python3 --version

The last command will return the Python version installed on your system. In my case, it is 3.12. Then, you can create and activate a Python virtual environment and install the libraries as follows:

sudo apt install python3.12-venv
python3 -m venv env1
source env1/bin/activate

pip install open-webui
open-webui serve

Note that in the first code line the number 3.12 should be replaced by your current Python version. The last command will start the Open-WebUI server. To start the GUI, go to your web browser, and enter the following address:

http://localhost:8080

This will start the GUI and the model can be selected from the top left corner.