Free LLM inference

Use any OpenAI-compatible tool with community GPUs. No credit card, no limits.

0
Models online
0
Donors online
0
Requests today
How it works
GPU Mesh is powered by community GPUs. Enthusiasts share spare compute — you get free inference.
1
Share
Donors run the agent, Ollama serves models. Anyone can contribute a GPU.
2
Match
The coordinator routes your request to an available donor with the model you need.
3
Use
Your tools just work — OpenAI-compatible API. No config changes needed.
Top models right now
No models online right now. Be the first donor!
Browse all models →