{"slug": "not-so-large-language-model-fits-on-a-floppy-disk", "title": "Not-So-Large Language Model Fits On a Floppy Disk", "summary": "Developer WollyMonjac published Tiny2.1, a 367K-parameter transformer chatbot that runs on DOS on a 486DX or Pentium processor and fits on a single floppy disk, with 380 KB of 8-bit weights and a 540 KB free-memory requirement. The Turbo C 2.0 code was written by Fable 5.2 and the model trained by Opus 5.5, and it holds 3,500 facts while otherwise generating fabricated answers. Training scripts for custom fact sets are available on GitHub under an MIT license.", "body_md": "At some point when hackers start pushing edge cases, nomenclature gets weird, like Large Language Models, or LLMs. At some point, the word “large” obviously becomes impossible to justify, but we’re not going to call [\\[WollyMonjac\\]’s Tiny2.1 DOS PC Chatbot](https://github.com/WollyMonjac/Tiny-2.1) just a ‘language model’ — perhaps “transformer” is the better term. That’s what LLMs and not-so-L-LMs like this one are under the hood, after all.\n\nIn any case, this one was written in Turbo C 2.0 by the no-debate ‘large’ LLM Fable 5.2 and trained by Opus 5.5. So for those of you who’ve got this one on their apocalypse bingo card: yes, machines are making machines. This second-gen transformer targets a 486DX or Pentium processor and runs on DOS, and you can get it onto the machine on a single period-appropriate floppy disk.\n\nThe actual network is 380 KB of 8-bit weights, while the rest of the floppy would hold the handy interface. As you might imagine, it needs 540 KB of free memory to run in. The transformer holds 3,500 facts in its 367K-parameter but outside of that it makes stuff up with the reckless abandon that these models [can’t escape, regardless of size.](https://hackaday.com/2025/10/10/your-llm-wont-stop-lying-any-time-soon/) \n\nThe project is of course more of a conversation-starter than anything else, though if you want to train it on your own 3,500 facts the scripts for that are on GitHub under an MIT license. We’ve seen [an LLM on a 486](https://hackaday.com/2025/04/19/will-it-run-llama-2-now-dos-can/) before, but being able to easily curate exactly what the model knows raises some interesting possibilities.", "url": "https://wpnews.pro/news/not-so-large-language-model-fits-on-a-floppy-disk", "canonical_source": "https://hackaday.com/2026/11/18/not-so-large-language-model-fits-on-a-floppy-disk/", "published_at": "2026-11-18 09:00:50+00:00", "updated_at": "2026-11-18 09:13:50.783570+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-research"], "entities": ["WollyMonjac", "Tiny2.1", "Turbo C 2.0", "Fable 5.2", "Opus 5.5", "GitHub", "DOS"], "also_reported_by": [], "takeaway": "A 367K-parameter transformer with 380 KB of 8-bit weights runs in 540 KB of DOS memory on a 486DX or Pentium and fits on one floppy, with MIT-licensed scripts to retrain its 3,500 facts.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/not-so-large-language-model-fits-on-a-floppy-disk", "markdown": "https://wpnews.pro/news/not-so-large-language-model-fits-on-a-floppy-disk.md", "text": "https://wpnews.pro/news/not-so-large-language-model-fits-on-a-floppy-disk.txt", "jsonld": "https://wpnews.pro/news/not-so-large-language-model-fits-on-a-floppy-disk.jsonld"}}