A thorough explainer on how quantization makes LLMs 4x smaller and 2x faster while losing only 5-10% accuracy. Covers floating point precision, compression techniques, and how to measure quality loss, with interactive examples throughout.
PHP
A tour of my dotfiles
Over the years, I’ve built up a collection of aliases, shell functions, and CLI tools that make my terminal feel like home. All of it lives in a single repository: my dotfiles. It’s a backup Read more…