Comparison video of Claude Code using Anthropics cloud models vs local models on a M4 128GB. Still a heavy lift, fans spinning, memory usage almost at full capacity. But it works. Means that for my M1 16GB a smaller model is all that works, and you need to leave room for context loading too. For one-offs like code generation and for interactive in moving contexts there's different needs.

one can run claude code using local models through the LM Studio endpoint. so that you don't use Claude in the cloud.

LM Studio model catalog (for local models). useful to see what is being used mostly at the mo

• [ ] return

https://web.archive.org/web/20251206203839/https://www.howtogeek.com/calibre-has-finally-given-into-the-ai-trend/

Calibre has added AI 'support', mostly to suggest new stuff to read and an option to discuss a book. It has an LM Studio back-end, so I can tie it to my local models.

LM Studio can run LLMs locally (I have llama and phi installed). It also has an API over a localhost webserver. I use that API to make llama available in Obsidian using the Copilot plugin.

This is the API documentation. #openvraag other scripts / [[Persoonlijke tools 20200619203600]] I can use this in?