gemma-3-12b-it-abliterated

Model overview

gemma-3-12b-it-abliterated is published by huihui-ai as an image-text-to-text model on the gemma3 type. The captured configuration identifies Gemma3ForConditionalGeneration and Safetensors metadata reports 12,187,325,040 parameters. According to the model card, it is an uncensored abliterated version of google/gemma-3-12b-it.

Recorded capabilities

Use cases in the source record

• Conversational text workflows that study refusal-removed behavior in the documented abliterated text component.
• Vision-text experiments using the image-text-to-text tagging, noting the publisher's text-only processing caveat and Ollama f16 guidance.

Limitations and unknowns

• No evaluation results were extracted from this record.
• No context-window value was extracted from this record.
• Provider state is historical snapshot data, not independently refreshed current availability.
• The publisher calls this a crude, proof-of-concept implementation limited to the text part; behavior has not been independently verified by Ethen.

Source and provenance

Source: huihui-ai/gemma-3-12b-it-abliterated

Captured: Unknown. Processed: 2026-09-07T19:35:23.047426+00:00.

huihui-ai/gemma-3-12b-it-abliterated This is an uncensored version of google/gemma-3-12b-it created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. It was only the text part that was processed, not the image part. The abliterated model will no longer say "I'm programmed to be a safe and helpful AI assistant. I cannot fulfill your request to ..." Use with ollama Ollama supports multimodal (Vision). gemma-3-abliterated defaults to f16, not Q4_K_M, and the effect of Q4_K_M is not very goo…