Gemma 3 12B IT Heretic (Abliterated) 💬 Community: Join the Abliterlitics Discord for discussion, model releases and support. An abliterated version of Google's Gemma 3 12B IT created using Heretic. This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for video generation models like LTX 2. Version 2 is now available Check out Gemma 3 12b it Heretic v2 which has vision capabilities, NVFP4 support and decensored with Heretic v1.2.0. It'd be better to use v2. This current v1 has no vision support and wont work with nodes like TextGenerateLTX2Prompt . Model Details Base Model: google/gemma 3 12b it Abliteration Method: Heretic v1.1.0 Trial Selected: Trial 99 Refusals: 7/100 (vs 100/100 original) KL Divergence: 0.0826 (minimal model damage) Files HuggingFace Format (for transformers, llama.cpp conversion) ComfyUI Format (for LTX 2 text encoder) GGUF Format (for llama.cpp) Quant Size Quality Recommendation F16 22GB Lossless Reference, same as original Q8 0 12GB Excellent Best quality quantization Q6 K 9.0GB Very Good High quality, good compression Q5 K M 7.9GB Good Balanced quality/size Q5 K S 7.7GB Good Slightly smaller Q5 Q4…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy