Raon-1 mini
A model from the Korean KRAFTON (the publisher of PUBG) with 30B parameters, 4B active, trained from scratch. It is strong in Korean conversation and agentic tasks: it can reason and call tools, and works with Hermes Agent, Pi and OpenCode. Training languages: Korean, English, Japanese, Chinese, Spanish, French, Thai, and Russian is not among them. There are compressed MXFP8 and NVFP4 versions and an auxiliary model for faster generation. This is a trial release (preview), and the specifications may change before the final one. The weights are issued on request on Hugging Face, and the benchmark figures are the authors' own.
- Developer
- KRAFTON AI, South Korea
- First release
- Oct 2026
- Latest release
- Oct 2026
- Sizes
- 30B-A4B
- License
- Commercial use allowedApache 2.0 (access to the weights on Hugging Face is issued on request)
- Russian
- Not stated
- Running
- On your own serverNeeds a GPU
- Industries
- Customer support, Software development, Media and production
What it does
- a Korean-language assistant and customer support
- an agent with tool calling on your own server
- game and media projects for a Korean audience
Where it is used
Hardware requirements
Versions
- Raon-1 mini preview (30B-A4B)
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can Raon-1 mini be used in a commercial project?
Yes. License: Apache 2.0 (access to the weights on Hugging Face is issued on request). It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does Raon-1 mini need?
At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does Raon-1 mini support Russian?
The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.
Where can I download Raon-1 mini and what does it cost?
The Raon-1 mini weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
A family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.
DetailsTextGLM (ChatGLM)Zhipu AI (Z.ai) · ChinaCommercial use with conditionsOne of the oldest Chinese open lines: from ChatGLM-6B to GLM-5.3. Strong at agentic tasks and programming; GLM-5.3-Flash understands images and is released under MIT.
DetailsText analysisHy-MemoryTencent Hunyuan · ChinaCommercial use allowedA model that runs the long-term memory of an AI agent: it decides what from a chat, work tasks or code is worth remembering, in what form, and how new information changes what is already stored. It replaces the general-purpose model inside the memory systems Mem0, MemOS and Tencent's own Hy-Memory. Languages on the card: English and Chinese. The benchmark figures are Tencent's own.
DetailsSource: huggingface.co/KRAFTON/Raon-1-mini-preview. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.