I built a tiny LLM to demystify how language models work
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
I built a tiny LLM to demystify how language models work launched on April 6, 2026 with 915 votes, #3 of 21,248 launches that month and more than 99% of that year's launches.
In plain words
This project is a minimal language model with approximately 9 million parameters built from scratch using a vanilla transformer architecture. It trains on 60,000 synthetic conversations in about five minutes on free cloud hardware, using roughly 130 lines of PyTorch code. Designed for people wanting to understand how language models work, it features a chatbot character whose responses reflect its training data—in this case, a fish obsessed with food. Users can fork the project and modify the training data to create their own character variations.
written from the facts on this page · September 2026
From the sources
A ~9M parameter LLM that talks like a small fish. Contribute to arman-bd/guppylm development by creating an account on GitHub.
This project exists to show that training your own language model is not magic. No PhD required. No massive GPU cluster. One Colab notebook, 5 minutes, and you have a working LLM that you built from scratch — data generation, tokenizer, model architecture, training loop, and inference. If you can run a notebook, you can train a language model. It won't produce a billion-parameter model that writes essays. But it will show you exactly how every piece works — from raw text to trained weights to generated output — so the big models stop feeling like black boxes. You> hi guppy Guppy> hi there. i just found a nice spot near the rock. the temperature feels nice. You> are you hungry Guppy> yes.…from github.com
Does a similar job
all alternatives →
Tiny-vLLM – high performance LLM inference engine in C++ and CUDAMay 2026 · github.com · ▲205Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM - jmaczan/tiny-vllm
Create-LLM – Train your own LLM in 60 secondsOct 2025 · github.com · ▲54https://medium.com/@theaniketgiri/three-months-ago-i-wanted-...
- TLTiny LLMs – Browser-based private AI models for a wide array of tasks2023 · tinyllms.vercel.app · ▲142
- WMWe made glhf.chat – run almost any open-source LLM, including 405B2024 · glhf.chat · ▲161
Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…
- ATA tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo)Aug 2026 · mikeayles.com · ▲79
A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay
Life & fun · Apr 2026 · sam-burns.com
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app
