ccharnkij/Qwen3.5-9B-Uncensored
ccharnkij/Qwen3.5-9B-Uncensored is a 9 billion parameter fine-tuned version of the Qwen3.5-9B model, developed by ccharnkij. This model removes default safety filters and refusal behaviors, enabling it to generate unrestricted and uncensored responses, including adult content. It retains the full multimodal capabilities of its base model, supporting both text and image understanding, making it suitable for research and educational applications requiring open-ended content generation.
Loading preview...
Overview
ccharnkij/Qwen3.5-9B-Uncensored is a 9 billion parameter language model derived from the Qwen/Qwen3.5-9B base model. It has been fine-tuned using LoRA (Low-Rank Adaptation) to remove inherent safety filters and refusal behaviors, allowing for the generation of uncensored and unrestricted content, including adult themes. The model is provided in the Safetensors format and maintains the multimodal capabilities of the original Qwen3.5-9B, supporting both text and image processing.
Key Capabilities
- Unrestricted Content Generation: Capable of producing responses that the base model would typically decline, including adult content.
- Multimodal Support: Retains the ability to understand and process both text and images.
- Refusal Behavior Removal: Eliminates default safety filters and censorship.
Use Cases
This model is primarily intended for research and educational purposes where the exploration of unrestricted language generation is required. A quantized GGUF version is also available for use with tools like llama.cpp, Ollama, and text-generation-webui, enhancing its accessibility for various experimental setups.