MiniArt Uncensored
MiniArt Uncensored by OSAMA INC is an unrestricted version of Mini Art, optimized for local inference on Qwen2 architecture. It delivers creative conversation, storytelling, and interactive dialogue — running entirely on your own hardware.
Available in GGUF format (Q4_K_M, ~379 MB) for seamless execution across LM Studio, Ollama, llama.cpp, and KoboldCpp.
Model Overview
| Property | Value |
|-------------------|--------------------------|
| Model Name | MiniArt Uncensored |
| Made By | OSAMA INC |
| Format | GGUF (.gguf) |
| Quantization | Q4_K_M (~379 MB) |
| License | Apache 2.0 |
| Context Length | 32768 tokens |
How to Use
LM Studio
1. Download MiniArt-Uncensored-Q4_K_M.gguf.
2. Open LM Studio and load the model file.
3. Start chatting.
Ollama
ollama create miniart-uncensored -f ./Modelfile
ollama run miniart-uncensoredllama.cpp
./llama-server -m MiniArt-Uncensored-Q4_K_M.gguf -c 2048 -n 512License
This project is licensed under the Apache 2.0 License.