Series · 4 parts
How LLMs Actually Run
What really happens between typing a prompt and getting an answer: the chips, the files, the memory, and why each one is the way it is. Start at part one; every post builds on the last.
Saif Bagmaru/25 min read in all- part01Why Can't Your Laptop Just Run ChatGPT?CPU vs GPU, explained from zero. Why AI needs a room full of expensive chips when you already own a powerful computer.
- part02What's Actually Inside an LLM File?Tensors, shapes, and precision — the numbers that make up a model, and why the same model can be 28 GB or 4 GB.
- part03How Models Are Packaged: pickle vs safetensors vs GGUFThe same numbers, three very different files — and why one of them could once run code on your machine.
- part04From Disk to Memory: How a Model's Weights Actually Get LoadedThe SSD → RAM → VRAM journey — and why loading can be nearly instant.
Start here
Part 1: Why Can't Your Laptop Just Run ChatGPT?
7 min read