Using an LLM or Large Language Model is a process that typically requires data being sent to a server. Local LLMs are different, as they allow you to process your prompts directly on your machine without the data you’re submitting to the local LLM leaving your computer.
The article makes an assumption that everyone know what LLMs are (which I don’t):
Opera blog post explain it better https://blogs.opera.com/news/2024/04/ai-feature-drops-local-llms/