Home Projects petals
petals
Python

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

by bigscience-workshop · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
Likely
Self-hostable
bloomchatbotdeep-learningMITPythonSelf-hostable
View on GitHub
In plain words

Run large language models at home to generate text quickly and efficiently, using your own computer.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
petals — GitHub preview card
📈 Star history
11k10k
2026-07-042026-08-31
📈 Track petals

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

petals has 10.5k stars on GitHub. It has been forked 643 times. petals is written mainly in Python. It has been in active development since 2022. petals is available under the MIT license. Its main topics are bloom, chatbot, deep-learning, distributed-systems.

Frequently asked questions

What is petals?

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

Is petals open source?

petals is an open-source project. It is released under the MIT license.

Is petals free?

Yes. petals is free and open source — you can use, modify and self-host it.

What license does petals use?

petals is available under the MIT license.

What language is petals written in?

petals is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — petals

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=bigscience-workshop-petals)](https://olud.ai/project/bigscience-workshop-petals.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.