Using Large Language Models
Large Language Models (LLMs) are powerful AI models capable of understanding and generating human-like text, making them essential for applications such as chatbots, content generation, code completion, and more.
In this guide, you will learn how to deploy and interact with LLMs in GPUStack.
Prerequisites
Before you begin, ensure that you have the following:
- A Linux machine with one or more GPUs that has at least 30 GB of VRAM in total. We will use the vLLM backend which only supports Linux.
- Access to Hugging Face or ModelScope for downloading the model files.
- GPUStack installed and running. If not, refer to the Quickstart Guide.
Step 1: Deploy Large Language Models
Deoloy from Catalog
Large language models in the catalog are marked with the LLM category. When you select a large language model from the catalog, the default configurations should work as long as you have enough GPU resources and the backend is compatible with your setup (e.g., vLLM backend requires an amd64 Linux worker).
Here, we take the deployment of Qwen3 0.6B as an example.
Follow these steps to deploy the model from Catalog:
- Navigate to the
Catalogpage in the GPUStack UI. - In the model list page, use dropdown to filter with
LLM. - Review the model description, maximum context length and supported sizes.
Deployment Using vLLM
- Select the
Qwen3 0.6Bfrom the catalog. - Change the model name and configuration as needed.
- Click the
Savebutton to deploy the model.
After deployment, you can monitor the model deployment's status on the Deployments page and wait for it to start running.
Step 2: Use the LLMs for Text Generation
- Navigate to the
Playground>Chatpage in the GPUStack UI. - Verify that the deployed model is selected from the top-right
Modeldropdown. - Provide a prompt for the text generation.
- Adjust the
Parameterson the right based on your needs. - Click the
Submitbutton to generate the text.
The generated chain of thought and result will be displayed in the UI.
By following these steps, you can leverage LLMs for AI-powered text generation and natural language tasks in GPUStack. Experiment with different prompts and settings to explore the full capabilities of LLMs!


