kitio.aiAdded Oct 29, 2026
Petals
FreeRun large language models together over a BitTorrent-style network
What is Petals?
Petals is an open-source system for running large models such as Llama 3.1 405B, Mixtral and BLOOM by splitting them across volunteers' machines. You load a small part of the model and rely on others to serve the rest.
Single-batch inference reaches a few tokens per second for 70B to 180B models, enough for chatbots and interactive apps, using a consumer GPU or Google Colab. Unlike hosted APIs, you can apply your own fine-tuning and sampling methods and even inspect hidden states, through a PyTorch and Hugging Face Transformers interface.
You can use the network or contribute your own GPU, and documentation lives on GitHub.
Features
- Distributed LLM inference
- Fine-tuning support
- PyTorch and Transformers API
- Access to hidden states
- Colab quickstart
Tags
Releases
+ Submit new release- Listed
Petals was added to the directory.
Organization
Petals open-source project
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Free
- Paid options from
- 100% free
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top Petals alternatives
View allModels & APIs
The main hub for open models, datasets and AI demo apps
Models & APIs
Run and deploy open-source AI models through a simple API
Models & APIs
Fast inference and fine-tuning platform for open models
Models & APIs
Cloud for running, fine-tuning and training open-source models
If you liked Petals
Low-cost serverless API for hundreds of open-source models
PaidModels & APIsMade in United StatesCompute, RL training, evals and inference for building your own models
PaidModels & APIsMade in United StatesOpen-source model serving and a managed platform for AI inference
FreemiumModels & APIsMade in United States
Pros and cons
Pros
- Runs very large models without owning big GPUs
- Full control over sampling and fine-tuning
- Free and open source
Cons
- Speed is only a few tokens per second
- Depends on volunteer servers
- Not suited to production traffic
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is Petals?
Petals is an open-source system for running large models such as Llama 3.1 405B, Mixtral and BLOOM by splitting them across volunteers' machines. You load a small part of the model and rely on others to serve the rest.
Do I need a big GPU?
No. The site says a consumer GPU or Google Colab is enough, since other participants serve the remaining model parts.
Can I fine-tune models?
Yes. You can apply any fine-tuning and sampling methods.
How much does Petals cost?
Petals is 100% free.
Is there a free version of Petals?
Yes. Petals is completely free to use.
What are the main features of Petals?
Distributed LLM inference, Fine-tuning support, PyTorch and Transformers API, Access to hidden states, Colab quickstart.
Who makes Petals?
Petals is made by Petals open-source project.
What are the best alternatives to Petals?
Popular alternatives include Hugging Face, Replicate, Fireworks AI.