The model it thinks with
An open-weight 9B model that's good at tool calling, run at 4-bit on llama.cpp. Small enough for a laptop: it's the size Luna is built for.
How it's tested
Luna is only as capable as the models it runs on. These are its defaults: what it runs every day, and what every change is tested against. Swap any of them for your own.
An open-weight 9B model that's good at tool calling, run at 4-bit on llama.cpp. Small enough for a laptop: it's the size Luna is built for.
A small model for finding things by meaning, a smaller one for background jobs like writing up a conversation, and speech, voices and pictures, all running locally.
Tested on Apple silicon Macs with 16 to 32 GB of memory. Where it's heading: a Mac mini at home, or a computer of your own elsewhere, always on for the whole family.
A set of the kinds of thing people actually ask, from “what's on tomorrow?” to “cover me for an hour”, each checked for whether it does the right thing.
Separate sets kept back on purpose, so it isn't only good at the examples it was shaped around.
Changes are measured against both before they go in. Anything that makes a request that used to work stop working is left out.
Yes. Any model your machine can run that handles tools will do. A bigger one on a bigger machine does better; a smaller one does less.
As better open models come out, yes. Whatever the default is, it's what everything is tested against.
Not to think. The models run on your machine; only things that are online by nature, like the web or email, need a connection.