In this day and age, you can’t expect to stay relevant if you are not learning or mastering various AI skills. One way to do so is by running your own AI models. The ConfiAI is a plug & play AI that lets you run gpt-oss, LLaMA, and other large language models. You don’t have to worry about tokens, fancy APIs, or even an internet connection. ConfiAI will be available in two models, with the C2 edge node ready for scaling. The C1 has a fanless design and offers GPU support.
The C1 model can handle LLMs up to 32B. The C2 can handle up to 120B models, making it ideal for larger teams. Thanks to this workstation, you can build and use your own private agents. It is also useful for chats and deep research. This project is getting funded on Kickstarter.
