Small qwen models are magical

It's so so good.

I have an app I've been working on for 2.5 years and felt kinda stupid making sure llama.cpp worked everywhere, including Android and iOS.

The 0.8B beats every <= 7B model I've used on tool use and can do RAG. Like you could ship it to someone who didn't know AI and it can do all the basics and leave UX intact.