Lucebox is a dedicated computer designed for local AI inference, pairing high-end hardware with a custom inference engine. It allows users to run large language models efficiently on-premises, with pre-installed software and open-source support, targeting AI enthusiasts and researchers.
Lucebox is a Foundation models & chat product. Enabling users to run large AI models locally with high efficiency and minimal setup. Lucebox is a consumer product aimed at AI enthusiasts and researchers. Pricing is paid, from $1999. The product ships for the web, the command line, macOS, Windows, and Linux, and it can be self-hosted.
Behind Lucebox is Lucebox, and the product first shipped in 2026. The project is developed in the open on GitHub with 2.6k stars and 1.2k commits in the last 90 days. Across PulseGate's embedding index, Lucebox has few near neighbours, marking it as relatively distinct. Among its 6 catalogued features are local inference, plug-and-play hardware, and optimized for LLMs.
Latest indexed changes and source events
A 35B MoE on a 16 GB GPU, without the offload tax discovered by the PulseGate indexer
Other apps tracked under the same category.
