Plain-AyI
← All projects
Run AI on your computer

llmfit

Checks your computer and tells you which AI models it can run well.

Fast-rising

What it does

Many AI chat models can run on your own computer, but bigger ones need more memory and a stronger graphics card. llmfit looks at your computer's processor, memory and graphics card, then scores models on how well they'd fit and how fast they'd run.

It can also suggest the right "quantization", a shrunk-down version of a model that uses less memory. It works with popular tools for running models locally, such as Ollama, llama.cpp and LM Studio, and can measure real speeds on your machine.

It runs as a simple screen inside the terminal, as a web dashboard, or as a regular command.

Who it's for

Anyone thinking of running AI models on their own computer who wants to know what will work.

Can I use it without coding?

With some setup. You install it with a single command (for example through Homebrew or Scoop) and use it in a terminal. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Linux, Windows
Computer
An ordinary computer is fine
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Install llmfit with Homebrew or Scoop, or download it from the project's releases page.
  2. Run llmfit in your terminal to see your hardware and a ranked list of models that fit.
Official download page

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it