What it does
HRM is a research model with two linked parts: one for slow, big-picture planning and one for fast, detailed work. Its makers say the design was inspired by the human brain.
The makers say it solves hard Sudoku puzzles and mazes after training on about 1,000 examples. The project shares code, training steps and some trained checkpoints; it needs graphics cards to run.
Who it's for
AI researchers and students interested in new approaches to AI reasoning.
Can I use it without coding?
Developers only. Running it needs programming skills and a graphics card. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Linux
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
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. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- Hierarchical Reasoning Model – 1k training samples SoTA reasoning v/s CoTHacker News · Jul 2025
- A 27M-param model that solves hard Sudoku/mazes where LLMs fail, without CoTHacker News · Jul 2025
- Hierarchical Reasoning ModelResearch paper · Jun 2025