Petals on a Mac
BitTorrent-style distributed inference of big models · AI Clusters
Petals runs large language models (e.g. Llama-class) collaboratively — you load a small slice of the model and connect over the public/private swarm to other peers serving the rest, BitTorrent-style, for inference and fine-tuning of models too big for local RAM. pip install petals; run a server with python -m petals.cli.run_server to contribute, or use the client to generate. Linux/CUDA-oriented; private swarms supported.
Run Petals with FrontierStack
FrontierStack lists Petals in its AI Clusters catalog. Install or connect it from one place, then monitor its status, ports and certificate, secure it with the firewall and Malware Audit, and back it up.
Run it all from one Mac app.
FrontierStack installs, monitors and secures the whole stack — locally and across your fleet — from a single native macOS app.
Download FrontierStack