Modelpublic

TheCluster/Gemma-4-26B-A4B-Heretic-MLX-mxfp4

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

3likes278downloads

Model Card

<div align="center"> <img src=https://ai.google.dev/gemma/images/gemma4_banner.png> </div> <div style="text-align:center; margin-bottom:12pt">If you like my work, you can <a href="https://donatr.ee/thecluster/">support me</a><br/></div>

Gemma-4-26B-A4B Heretic

Quality: quantized (*mxfp4, 4.604 bpw*)

This is a abliterated (uncensored) version of google/gemma-4-26B-A4B-it, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method (with row-norm preservation)

Performance

Metric	This model	Original model ([google/gemma-4-26B-A4B-it](https://huggingface.co/google/gemma-4-26B-A4B-it))
KL divergence	0.0499	0 (by definition)
Refusals	11/100	100/100

Abliteration parameters

Parameter	Value
start_layer_index	10
end_layer_index	30
preserve_good_behavior_weight	0.5480
steer_bad_behavior_weight	0.0009
overcorrect_relative_weight	0.5868
neighbor_count	14

Source

This model was converted to MLX format from `coder3101/gemma-4-26B-A4B-it-heretic` using mlx-vlm version 0.4.4.