Tiny, blunt, and faster than your typing.
Sao10K · Llama 3 8B · 8B parameters · 8K context · Pro $20/mo · Censorship: none
Lunaris is Sao10K's Llama 3 8B tune — a generalist merge built for creative writing and roleplay at the smallest practical size. There's no pretense here: it won't out-think a 70B. What it does is answer instantly, bluntly, and without filters, which is exactly what a lot of conversations actually need.
Think of it as the snappy second screen: quick questions, fast RP exchanges, idea pings, mobile sessions where you want texting-speed replies. It's also the gentlest way to learn how uncensored models behave before stepping up the lineup.
Speed-first chat: quick questions, casual roleplay, idea riffing, and mobile use. It's deliberately small — instant answers over deep analysis.
When answers start feeling shallow or a story needs more memory — its 8K context is the smallest in the lineup. Euryale 70B is the natural step up; OpenRogue lets you switch mid-chat.
Yes — like the rest of the OpenRogue lineup, it answers directly without filters or lectures.
Related models: Rocinante · Dolphin Venice · Euryale