Skip to content

Search wahloon.net

Search models, news, guides and FAQs.

Model catalog
Gemma12BAbliteration~8 GB

Huihui-gemma-4-12B-it-abliterated

google/gemma-4-12b-it

Solid mid-size Gemma 4 abliterated variant from the most active publisher.

Run it

Ollama

The publisher provides an Ollama tag. Pull it directly:

ollama run huihui_ai/gemma-4-abliterated:12b

Download the weights

Uses the Hugging Face CLI. Install it with pip install -U huggingface_hub if needed.

hf download huihui-ai/Huihui-gemma-4-12B-it-abliterated

LM Studio / llama.cpp

In LM Studio, search for the repository name and pick a GGUF quant that fits your VRAM. With llama.cpp, use llama-cli -hf huihui-ai/Huihui-gemma-4-12B-it-abliterated. See the setup guide for full flags and sampling defaults.

Formats & tags

GGUFTransformers

Listed quantizations: GGUF, Transformers.

#gemma#abliterated#12b

Notes

Solid mid-size Gemma 4 abliterated variant from the most active publisher.

Method: abliteration. License: Apache-2.0 / Gemma. Last catalog update: Nov 11, 2026. This entry links to a third-party repository; wahloon.net is not affiliated with the publisher. Verify the current model card, license and file list before downloading. You are responsible for how you use the model.

Browse all
Gemma31B
Heretic-ARA

gemma-4-31B-it-uncensored-heretic

google/gemma-4-31b-it

Larger Gemma 4 Heretic build with reported strong refusal reduction.

Approx. VRAM
~18–19 GB (Q4)
License
Apache-2.0
Downloads
720K / 30d
#gemma#31b#heretic#ara

updated Nov 7, 2026

Gemma27B
Abliteration

gemma-3-27b-it-abliterated

google/gemma-3-27b-it

Well-known earlier abliteration by mlabonne. Still widely referenced.

Approx. VRAM
~16 GB
License
Gemma
Downloads
180K / 30d
#gemma#classic#abliterated

updated Apr 1, 2025