Ollama Use Cases

This guide walks you through inferencing deepseek-r1:1.5b model using Ollama and OpenWebUI with supported NVIDIA GPU H100.

1. Step 1: Create a GPU Container using Ollama-OpenWebUI template'

2. Step 2: Create root user for OpenWebUI

3. Step 3: In this tutorial, we will use the deepseek-r1:1.5b model as an example. Feel free to choose a different model that best suits your needs.

4. Step 4: After pulling successfully, send a prompt to test the model