Category Main

When news started coming out about coding assistants moving to token-based pricing, I thought it was a good time to see how far I could get with a fully local setup. For this whole experiment, I used a three-year-old MacBook…

One of the biggest challenges when getting started with local LLMs is choosing the right model for your use case. There are hundreds of options available, all with different strengths, hardware requirements, context sizes, and reasoning capabilities. A model that…