Yaarbal — the open model library.
Contribute compute, access every model.
Yaarbal is an open, BitTorrent-inspired peer-to-peer network for LLM inference. Anyone can host a seeder for a model they care about; anyone can run inference against the swarm. Install once, every model in the registry is one command away.
Try it in 2 minutes
Python 3.11 or newer. macOS or Linux. Pulls a ~600 MB Qwen 2.5 0.5B model on first run.
pip install yaarbal && yaarbal run qwen2.5-0.5b-instruct "hello"
How it works
Seeders host complete models and earn credits. Leechers spend credits to run inference. The tracker matches them — no central inference provider.