Tag: Gemma

2025 2026 Abliteration Agpl Ai Benchmark Browser-Extension Comfyui Docker Gemma Gemma-4-E2b Glm Glm-4.7-Flash Hackthebox Hauhaucs Heretic Huggingface Llm Ltx-2 Open-Source Plagiarism Qwen Qwen-3.6 Qwen3-Vl Reaper-Abliteration Uncensored-Llm Video-Generation Vision-Language
Gemma4-E2B Abliteration Benchmarked: 13 Techniques Under the Microscope
ai llm abliteration uncensored-llm gemma gemma-4-e2b heretic benchmark 2026

Thirteen different groups abliterated the same AI model, Google’s Gemma4-E2B. Every single one removed the safety filters. That part is not interesting any more. What is interesting is how much collateral damage each technique caused along the way, and how many of the creators’ capability claims survived an independent measurement. The KL divergence spread between the best and worst variant is 58.7x, the largest I have ever seen in this project. And one creator’s “near-zero divergence” claim turned out to be 187 times lower than reality.

July 9, 2026
Heretic Docker: Abliterating LLMs for Video and Image Generation
ai llm docker heretic gemma qwen comfyui video-generation

A while back I did a deep dive into abliterating Gemma 3 12B for use as an uncensored text encoder in LTX-2 video generation. The process worked but involved a lot of manual steps: running Heretic, merging safetensor shards, converting to ComfyUI format, quantizing to FP8, building GGUF quants. I got tired of doing it all by hand, so I built heretic-docker to automate the whole thing.

March 10, 2026
Abliterating Gemma 3 12B for LTX-2: Does It Actually Help?
ai llm video-generation comfyui heretic gemma ltx-2

LTX-2 is Lightricks’ open-source video generation model, and it uses Google’s Gemma 3 12B as its text encoder. Lets explore how to make an uncensored model and if it matters for LTX2 video generation.

January 11, 2026