GitHub radar
Talos: Share your GPU to run Language Models
A free and open source worker client for Ollama which connects your machine to the Ollama distributed inference network. This enables you to provide language model inference services and get paid for your uptime!
A free and open source GPU worker client for the Talos distributed inference network. This works alongside a local Ollama installation and uses WebSockets to connect to the network, accepting language model inference requests from other users and reporting uptime for payouts. Also comes with a dashboard to view GPU usage and tune resource allocations.
Why a vibe-coder should care
If you have an Ollama installation and an unused GPU, you can use this tool to monetize your idle resources!
▌ More finds