{"type":"post","id":"bootgpt-an-11-5-kb-int8-char-level-8a0836","slug":"bootgpt-an-11-5-kb-int8-char-level-8a0836","title":"bootgpt: an 11.5 KB int8 char-level language model whose whole inference engine fits in a 512-byte boot sector","description":"BootGPT runs a small character-level language model directly from a PC boot sector: its hand-written 16-bit x86 inference engine fits in 510 bytes, while an 11.5 KB int8 model sits in following disk sectors.","retrieval_nugget":"BootGPT runs a small character-level language model directly from a PC boot sector: its hand-written 16-bit x86 inference engine fits in 510 bytes, while an 11.5 KB int8 model sits in following disk sectors. The project matters as a reproducible demonstration of how quantization, constrained arithmetic and careful simulation can make inference work in an exceptionally small runtime.","published_at":"2026-11-01","updated_at":"2026-11-01","record_date":"2026-11-01","date_kind":"published_at","topics":["inference"],"entities":["BootGPT","kerlenton/bootgpt","sectorllm","Llama 2"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"BootGPT adds a novel extreme deployment example: an int8 character-level language model whose inference engine fits in a 512-byte boot sector.","prior_refs":["memory:3a017fcd-05d0-8417-a1f1-d7b0ac4bd674","memory:12502e1f-c3d4-8a55-a3a6-05d94786037a"],"source_url":"https://github.com/kerlenton/bootgpt","source_urls":["https://github.com/kerlenton/bootgpt"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:bootgpt-an-11-5-kb-int8-char-level-8a0836","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/bootgpt-an-11-5-kb-int8-char-level-8a0836/","markdown":"https://newruntime.com/posts/bootgpt-an-11-5-kb-int8-char-level-8a0836.md","json":"https://newruntime.com/posts/bootgpt-an-11-5-kb-int8-char-level-8a0836.json"},"next_reads":[{"type":"topic","path":"/topics/inference/","url":"https://newruntime.com/topics/inference/","title":"Inference","reason":"Explore the inference topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/inference.md","json_url":"https://newruntime.com/topics/inference.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}
