TheCluster/Gemma-4-31B-Heretic-MLX-8bit

Gemma-4-31B Heretic

Quality: quantized (8 bit, group size: 32, 8.802 bpw)

This is a abliterated (uncensored) version of google/gemma-4-31B-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-4-31B-it)
KL divergence	0.0434	0 (by definition)
Refusals	15/100	99/100

Abliteration parameters

Parameter	Value
start_layer_index	1
end_layer_index	59
preserve_good_behavior_weight	0.8438
steer_bad_behavior_weight	0.0002
overcorrect_relative_weight	1.0760
neighbor_count	15

---

Source

This model was converted to MLX format from coder3101/gemma-4-31B-it-heretic using mlx-vlm version 0.4.4.