Personal AI Computer
An open-source hardware guide, with parts lists, CAD and assembly photos, for building your own local machine to run large language models instead of renting inference from a cloud provider.
This repository is the open-source hardware side of a project for building a personal machine dedicated to running AI models locally. It documents five builds, from an entry-level machine with two NVIDIA RTX 5090 GPUs and 64 GB of combined VRAM up to larger configurations, each with a parts list, CAD files, BIOS settings and assembly photos, so a reader can order the parts and assemble the same machine themselves.
A finished, pre-built machine can also be ordered directly for readers who prefer not to source parts and assemble the hardware. The project pairs the open hardware with a choice of open-source local AI software, such as the maintainers' own Grid orchestrator, or alternatives including vLLM, Ollama and llama.cpp.