GitHub Models, running AI models from a Linux terminal

I recently bought an old ThinkPad T470p for 150 euros, and it still felt surprisingly agile even with the factory-installed Windows 10. After a brief testing phase, I quickly got rid of the pre-installed bloatware and installed the latest Linux Mint 22.1, which made it more responsive than my work ThinkPad T14 that, unfortunately, suffers from Windows 11 due to company policies. Fast or slow, these laptops are no longer powerful enough to run advanced AI models—even with 32 GB of RAM, they can only handle smaller models. However, this is where the GitHub CLI becomes very useful; a new add-on called GitHub Models was recently released that allows you to try out several models. 

ThinkPad T470p, the legendary office workhorse of the 2010s
ThinkPad T470p, the legendary office workhorse of the 2010s

The first step, if you don’t already have it, is to install the GitHub CLI. The GitHub CLI comes with excellent documentation that explains what to do for many Linux distributions—you can access it here. For Linux Mint or any other Ubuntu- or Debian-based distribution, you can use the following command: 

(type -p wget >/dev/null || (sudo apt update && sudo apt-get install wget -y)) \
        && sudo mkdir -p -m 755 /etc/apt/keyrings \
    && out=$(mktemp) && wget -nv -O$out https://cli.github.com/packages/githubcli-archive-keyring.gpg \
    && cat $out | sudo tee /etc/apt/keyrings/githubcli-archive-keyring.gpg > /dev/null \
        && sudo chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg \
        && echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" | sudo tee /etc/apt/sources.list.d/github-cli.list > /dev/null \
        && sudo apt update \
        && sudo apt install gh -y

 Once this is done, log in by typing gh auth login. This will open your browser for the login process. After you’re logged in, install the GitHub Models add-on with the command

gh extension install https://github.com/github/gh-models

and you’re ready to run the models. First, let’s see which models are available by using the command gh models list. At the time of writing, there were 41 chat models available. 

The list of the models
The list of the models

 To run a selected model, type gh models run <model>, or simply type gh models run and choose the model interactively. For example, to run the OpenAI GPT-4o model, you would type:

gh models run gpt-4o

Running of a model
Running of a model

To exit, type /exit

Share this post
Apple’s AI Doctor Plans
Apple is developing an AI-powered health coach, codenamed “Project Mulberry,” designed to give personalized advice for everyday life. The new feature is expected to be included in a future iOS 19.4 update—likely in spring or summer 2026—and will first launch in the US.
 Credit-based Windows Notepad usage with Copilot integration
Microsoft is introducing a new feature in Windows Notepad that allows you to use Microsoft Copilot, an artificial intelligence to improve your writing in Notepad. The feature allows you to rephrase your writing, generate a summary, or make other text tweaks such as adjusting the tone or style of text.
Zorin OS 17.3 with the Most User-Friendly GNOME Desktop Environment
Released on March 26, 2023, Zorin OS 17.3 introduces several new features to enhance the user experience, security, and system compatibility.
TxGemma - New Open Model for Drug Development
One of the biggest challenges in drug development is finding lead compounds beyond the clinical phase, as 90% of candidates fail in the initial trial phase. In this context, TxGemma—an open model collection developed on top of Google's DeepMind Gemma and its family of modern, lightweight open models—represents a breakthrough. TxGemma aims to harness the power of large language models to improve the efficiency of therapeutic discovery, from identifying promising targets to predicting clinical trial outcomes.