Deploy the QwQ‑32B LLM on Alibaba Cloud Function Compute with CAP in Minutes

Solution Overview

This guide shows how to deploy the open‑source QwQ‑32B large language model on Alibaba Cloud Function Compute (FC) using the Cloud Application Platform (CAP). Two serverless functions are created: Ollama to host the QwQ‑32B‑GGUF model and Open WebUI to provide a web UI for interactive chat.

Architecture

One CAP project that runs the Ollama and Open WebUI functions.

A NAS file system attached to the project for persisting the model files.

Prerequisites

Alibaba Cloud account (register at https://account.aliyun.com/register/qr_register.htm if you do not have one).

Enable Function Compute service in the console (https://fcnext.console.aliyun.com/) and grant the required permissions.

Deployment Procedure

1. Create CAP Project

Open the CAP console: https://cap.console.aliyun.com/create-project?template=194&from=solution.

Select the "QwQ‑32B" template, choose a region (e.g., China Beijing 2), keep default settings, and click Deploy Project .

Confirm the deployment; the provisioning takes about 10–12 minutes.

2. Locate Access URL

After deployment, open the CAP project details page and copy the generated HTTP endpoint.

Open the endpoint in a browser; the Open WebUI interface appears.

3. Test the Model

Enter a prompt such as "Who are you?" in the text box and submit. The model returns a response.

4. Adjust Ollama Scaling

In the CAP console, edit the Ollama function configuration and increase the reserved instance count to enable horizontal scaling.

5. Access via Chatbox Client

Copy the Ollama API endpoint shown in the CAP console.

Download the Chatbox client (https://chatboxai.app/zh#download) and install it (the screenshots show macOS M3).

In Chatbox, open Settings and configure:

Save the configuration.

Now you can type queries (e.g., "Who are you?" ) in Chatbox and receive responses from the deployed QwQ‑32B model.

Resource Cleanup

When the demo is finished, delete the CAP project to stop incurring charges:

Log in to the CAP console (https://cap.console.aliyun.com/).

Navigate to Projects , locate the deployed project, click Delete , and confirm the deletion.

Cost Considerations

The free trial quotas for Function Compute and NAS are sufficient for the steps in this guide. If the trial limits are exceeded, the estimated cost is below ¥9 per hour, but actual charges depend on the number of GPU instances and runtime duration. Always verify the final bill in the Alibaba Cloud console.

Reference URLs

Account registration: https://account.aliyun.com/register/qr_register.htm

Function Compute console: https://fcnext.console.aliyun.com/

Free trial details: https://help.aliyun.com/document_detail/2665971.html

NAS file storage: https://free.aliyun.com/?searchKey=%E6%96%87%E4%BB%B6%E5%AD%98%E5%82%A8+NAS

CAP project template: https://cap.console.aliyun.com/create-project?template=194&from=solution

Chatbox download: https://chatboxai.app/zh#download