Qwen3.5: Turn an Old PC into an AI Agent with Ollama and OpenCode

Transforming an Old Laptop into an AI Agent

With advancements in open-source tools, it is now possible to run powerful AI models on modest machines. The Qwen3.5 model, in combination with Ollama and OpenCode, allows you to transform an old laptop into a local AI environment. This solution provides an accessible alternative for coding and experimentation without the need for expensive hardware.

Running a powerful AI model locally no longer requires a high-end workstation or an expensive cloud setup. Thanks to lightweight tools and smaller open-source models, even an old laptop can become a practical AI environment for coding, experimentation, and agent-like workflows.

Installing Ollama

To run Qwen3.5, the first step is to install Ollama, a tool that facilitates the local execution of large language models. Windows users can install Ollama via PowerShell with the following command:

irm https://ollama.com/install.ps1 | iex

The Ollama download page also includes installation instructions for Linux and macOS, so you can follow the steps there if you are using a different operating system. Once the installation is complete, you will be ready to start Ollama and download your first local model.

Starting Ollama

After installation, Ollama starts automatically, especially on the first use. This means you may not have to do anything else before running a model locally. If the Ollama server is not already running, you can start it manually with the following command.

Running Qwen3.5

With Ollama running, you can download and execute the Qwen3.5 model. For this tutorial, the 4B version is recommended, as it offers a good balance between performance and hardware requirements, needing about 3.5 GB of RAM. To launch the model, use the command:

ollama run qwen3.5:4b

The first time you run this command, Ollama will download the model files to your machine. Depending on your internet speed, this may take a few minutes. After the download is complete, Ollama may take a moment to load the model and prepare everything necessary to run it locally. Once ready, you will see an interactive terminal chat interface where you can start querying the model directly.

At this point, you can already use Qwen3.5 in the terminal for simple local conversations, quick tests, and light coding assistance before connecting it to OpenCode for a more agent-like workflow.

Installing OpenCode

Once you have set up Ollama and Qwen3.5, the next step is to install OpenCode, a local coding agent that can work with models running on your own machine. You can visit the OpenCode website to explore the available installation options and learn more about how it works. For this tutorial, we will use the quick installation method as it is the simplest way to get started.

Run the following command in your terminal:

curl -fsSL https://opencode.ai/install | bash

This installer manages the setup process for you and installs the required dependencies, including Node.js if necessary, so you don’t have to configure everything manually.

Launching OpenCode with Qwen3.5

Now that Ollama and OpenCode are installed, you can connect OpenCode to your local Qwen3.5 model and start using it as a lightweight coding agent. If you look at the Qwen3.5 page in Ollama, you will notice that Ollama now supports simple integrations with external AI tools and coding agents. This makes it much easier to use local models in a more practical workflow rather than just chatting with them in the terminal.

To launch OpenCode with the Qwen3.5 4B model, run the following command:

ollama launch opencode --model qwen3.5:4b

This command tells Ollama to start OpenCode using your locally available Qwen3.5 model. After running it, you will be directed to the OpenCode interface with Qwen3.5 4B already connected and ready to use.

Creating a Python Project

With OpenCode and Qwen3.5, you can start giving it simple prompts to create software directly from your terminal. For this tutorial, we asked it to create a small Python game project from scratch using the following prompt:

Create a new Python project and build a modern "Guess the Word" game with clean code, simple gameplay, score tracking, and an easy-to-use terminal interface.

After a few minutes, OpenCode generated the project structure, wrote the code, and handled the necessary configuration to get the game running. We also asked it to install all required dependencies and test the project, which made the workflow much closer to that of a lightweight local coding agent than just a simple chatbot.

The final result was a fully functional Python game that ran smoothly in the terminal. The gameplay was simple, the code structure was clean, and the score tracking worked as expected. For example, when you enter a correct character, the game immediately reveals the corresponding letter in the hidden word, showing that the logic works correctly from the start.

Limitations and Considerations

While this solution is convenient for simple projects, it has limitations for more complex tasks. Because this setup relies on a smaller and quantized model, the results are not always robust enough for more complex coding tasks. In my experience, it can handle simple projects, basic scripts, research assistance, and general tasks quite well, but it starts to struggle when software engineering work becomes more demanding or multi-step.

One issue I encountered repeatedly was that the model sometimes stopped mid-task. When this happened, I had to manually type "continue" for it to proceed and finish the work. This is manageable for experimentation, but it makes the workflow less reliable when you want a consistent outcome for larger coding tasks.