bootgpt: a language model that lives in a 512-byte boot sector
bootgpt packs a tiny character-level neural network into a PC's master boot record: 510 bytes of hand-written 16-bit assembly load an int8 model from the following disk sectors and run it in real mode on a 386, with no OS or runtime. The 11,520-parameter model, trained on synthetic Linux boot logs, generates plausible dmesg-style output as the machine boots. An independent reproduction verified the assembly byte-for-byte.
Why it matters
The extreme end of tiny-model engineering: a working neural network executing before any operating system exists, proving integer-only inference can live in the most constrained environment imaginable.
What you could build with it
A computer-science instructor could use the project as a teaching demo: students assemble a 512-byte boot sector and watch a tiny neural network generate boot logs on bare hardware, making quantization and integer-only inference tangible instead of abstract.
Does it hold up?
Too early to judge beyond the stunt: one independent reproduction confirms the assembly and weights are exactly as claimed, but there is no practical application yet — its value is educational, showing how far quantization and integer math can be pushed.
Built with bootgpt
Learn more
official docs →
First spotted on github: source.
More AI models
VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72NVIDIA Cosmos 3.5 world models: now openly availableNVIDIA's Cosmos 3.5 family of open world foundation models for robots, autonomous vehicles and vision agents is now…models · JEV 0.71 Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.