LastRef/gemma-3-12b-it-heretic-x

VISIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:Dec 23, 2025License:gemmaArchitecture:Transformer0.0K Cold

LastRef/gemma-3-12b-it-heretic-x is a 12 billion parameter instruction-tuned multimodal language model, derived from Google's Gemma 3 family, with a 32K token context window. This specific variant is a decensored version created using the Heretic tool and a custom x-rated dataset, outperforming other Gemma-3-12b-it ablations in internal NSFW evaluations. It excels in writing categories among Gemma-3-12b models, making it suitable for applications requiring less restrictive content generation.

Loading preview...

LastRef/gemma-3-12b-it-heretic-x: Decensored Multimodal Gemma 3

This model is a 12 billion parameter instruction-tuned variant of Google's Gemma 3, specifically engineered by LastRef as a decensored version using the Heretic tool. Unlike typical Heretic models, it was developed with a custom x-rated dataset and fine-tuned for less restrictive content generation. It maintains the multimodal capabilities of the base Gemma 3, handling both text and image inputs to generate text outputs, with a 32K token context window.

Key Capabilities

  • Decensored Content Generation: Optimized for producing less restricted and x-rated content, outperforming other Gemma-3-12b-it ablations in internal NSFW evaluations.
  • Multimodal Input: Processes both text and image inputs (images normalized to 896x896 resolution, encoded to 256 tokens each).
  • Strong Writing Performance: Achieves the 2nd place in writing categories for Gemma-3-12b models on the UGI-Leaderboard.
  • Broad Language Support: Inherits multilingual support in over 140 languages from the base Gemma 3.

Good For

  • Applications requiring decensored or x-rated text generation.
  • Creative writing and roleplay scenarios with fewer content restrictions.
  • Research and experimentation into model safety and content filtering bypasses.
  • Multimodal tasks such as image analysis combined with unrestricted text generation.