Photo by author
# Introduction
High-end workstations or expensive cloud setups are no longer required to run high-performance AI models locally. With lightweight tools and small open-source models, you can now turn even an old laptop into a practical native AI environment for coding, experimentation, and agent-style workflows.
In this tutorial, you will learn how to walk. Qwen3.5 Using locally Allama And attach it Open code To create a simple local agent setup. The goal is to keep everything straightforward, accessible, and beginner-friendly, so you can get a working native AI assistant without having to deal with a complex stack.
# Installing Ulama
The first step is to install Olama, which makes it easy to run large language models natively on your machine.
If you are using Windowsyou can either download Olama directly from official. Download Olama on Windows. Build the page and install it like any other application, or run the following command. PowerShell:
irm | iex
The Olama download page also includes installation instructions. Linux And macOSso if you are using a different operating system you can follow the steps there.
After the installation is complete, you’ll be ready to launch Olama and draw your first local model.
# Ulama are starting.
In most cases, Olama starts automatically after installation, especially when you launch it for the first time. This means you won’t need to do anything else before running the model locally.
If the Olama server is not already running, you can start it manually with the following command.
# Running Qwen3.5 locally.
After running Olama, the next step is to download and launch Qwen3.5 on your machine.
If you look at the Qwen3.5 model page at Ulama, you’ll see a number of model sizes, ranging from larger variants to smaller, more lightweight options.
For this tutorial, we’ll use the 4B version because it offers a good balance between performance and hardware requirements. This is a practical choice for older laptops and typically requires around 3.5 GB of random access memory (RAM).
To download and run the model from your terminal, use the following command:
The first time you run this command, Olama will download the model files to your machine. Depending on your internet speed, this may take a few minutes.
After the download is complete, Olama may take some time to load the model and prepare everything needed to run it locally. Once ready, you will see an interactive terminal chat interface where you can start prompting the model directly.
At this point, you can already use Qwen3.5 in the terminal to support simple native conversations, quick tests, and lightweight coding before connecting it to OpenCode for a more agentic workflow.
# Installing Open Code
After setting up Ollama and Qwen3.5, the next step is to install OpenCode, a native coding agent that can work with models running on your own machine.
You can visit the open source website to explore the available installation options and learn more about how it works. For this tutorial, we’ll use the quick install method because it’s the easiest way to get started.
Run the following command in your terminal:
curl -fsSL | bashThis installer handles the setup process for you and installs required dependencies, including Node.js When needed, you don’t need to configure everything manually.
# Launching Open Code with Qwen3.5
Now that both Olama 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 see that Ollama now supports simple integration with external AI tools and coding agents. This makes it much easier to use local models in a more practical workflow than just chatting in the terminal.
To launch OpenCode with the Qwen3.5 4B model, run the following command:
ollama launch opencode --model qwen3.5:4bThis command tells Olama to initialize OpenCode using your locally available Qwen3.5 model. After it runs, you will be taken to the Open Code interface with Qwen3.5 4B pre-installed and ready to use.
# Creating a Simple Python Project with Qwen3.5
Once OpenCode is up and running with Qwen3.5, you can start giving it simple commands to build software directly from your terminal.
For this tutorial, we asked to make it a small one The python Start the game project using the following prompt:
Create a new Python project and create 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 created the project structure, wrote the code, and handled the setup needed to run the game.
We also asked it to install any required dependencies and test the project, which made the workflow feel much closer to working with a lightweight native coding agent than a simple chatbot.
The end result was a fully functional Python game that ran smoothly in Terminal. The gameplay was simple, the code structure was clean, and the score tracking worked as expected.
For example, when you enter the correct letter, the game immediately reveals the matching letter in the hidden word, indicating that logic works correctly out of the box.
# Final thoughts
I was really impressed with how easy it was to run a local agent setup on an old laptop with Olama, Qwen3.5, and OpenCode. For a lightweight, low-cost setup, it works surprisingly well and makes native AI feel more practical than many might expect.
That said, it’s not all smooth sailing.
Because this setup relies on a small and quantized model, the results are not always robust enough for more complex coding tasks. In my experience, it can handle simple projects, basic scripting, research support, and general-purpose tasks well, but it starts to struggle when software engineering work becomes more demanding or multi-step.
One problem I saw repeatedly was that the model would sometimes stop halfway through a task. I had to manually type when this happened Continue To continue it and finish the job. This is manageable for experimentation, but makes the workflow less reliable when you want consistent output for large coding tasks.
Abid Ali Awan (@1abidaliawan) is a certified data scientist professional who loves building machine learning models. Currently, he is focusing on content creation and writing technical blogs on machine learning and data science technologies. Abid holds a Master’s degree in Technology Management and a Bachelor’s degree in Telecommunication Engineering. His vision is to create an AI product using graph neural networks for students struggling with mental illness.