Raon-1 mini preview
A chat model from KRAFTON, a Korean company, that may soon be free to download and run on your own computer, mainly for developers.
Not confirmed yet. The maker hasn't announced this. trckr spotted it via GitHub ggml-org/llama.cpp, which makes it an Early signal: A hint that a model is coming before it's announced: a name spotted in a lab's systems, an anonymous test model, or code that adds support for it. Usually right, sometimes not.: usually right, but details may change or turn out to be wrong.
Key facts
- Released
- Nov 13, 2026
- What it does
- Text and chat: Writes, answers questions and holds a conversation.
Can I use it?
Not officially released yet. Here's what's known so far; trckr updates this page when it launches.
In an app
No app mentioned so far.
For developers
No developer access mentioned so far.
Download
Free to download and run on your own computer: it has Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open"..
The details
A llama.cpp pull request suggests KRAFTON's Raon-1 mini Preview: An early version released for testing. It may change or disappear, and is often limited while it lasts., a 30B Mixture of experts (MoE): A design that splits a big model into many "expert" parts and uses only a few for each word. It gives big-model quality at closer to small-model speed. text model under Apache 2.0, may be coming to local Inference: Running a trained model to get an answer. Training builds the model once; inference happens every time someone uses it..
Timeline
/GitHub ggml-org/llama.cppFirst signal
model : add RAON-1-mini-preview support (ggml-org/llama.cpp #32173)
Get alerts like this the moment they happen.
From every major lab.