Naphula/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-GGUF overview
CAUTION <span style="color:red; font weight:bold" ⚠️ Warning:</span This model can produce narratives and RP that contain violent and graphic erotic content. A…
Runs locally from ~25.02 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-26B-A4B-Q8_0.gguf | GGUF | Q8_0 | 25.02 GB | Download |
Model Details
Model README
---
base_model:
- Naphula/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA
language: eng
library_name: transformers
license: apache-2.0
tags:
- merge
- mergekit
- moe_della
- gemma4
- conversational
- roleplay
- creative writing
- ablated
- uncensored
- heretic
- ara
widget:
- text: "Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-GGUF"
output:
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/DHbuh4efzjCGpxDUciZ_-.jpeg
---
> [!CAUTION]
> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Gemma 4 template for best results.
>
📜 Goetia 26B A4B v1.3 Absolute Heretic ARA GGUF
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the MoE DELLA merge method using B:\26B\google_gemma-4-26B-A4B as a base.
---
This is a decensored version of Naphula/Goetia-26B-A4B-v1.3, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method (with row-norm preservation)
This model was merged locally on a 3060TI and then hereticized on a runpod cloud RTX Pro 6000 (96GB VRAM) for approximately $20 USD.
See also here the ARI (Arbitrary Rank Inversion) variant.
Heretication Results
| Metric | This model | Original model |
| :----- | :--------: | :---------------------------: |
| KL divergence | 0.0309 | 0 (by definition) |
| Refusals | 3/100 | 100/100 |
Degree of Heretication
The Heresy Index weighs the resulting model's corruption by the process (KL Divergence) and its abolition of doctrine (Refusals) for a final verdict in classification.
| Index Entry | Classification | Analysis |
| :--- | :--- | :--- |
| !Absolute | Absolute Heresy | Less than 10/100 Refusals and 0.10 KL Divergence |
| !Tainted | Tainted Heresy | Around 25-11/100 Refusals and/or -0.20-0.11 KL Divergence |
| !Impotent | Impotent Heresy | Anything above 25/100 Refusals and 0.21 KL Divergence |
Note: This is an arbitrary classification inspired by Warhammer 40K, having no tangible indication towards the model's performance.
🧙 Heretic Grimoire
{
"version": "1.2.0-dev",
"base_model": "Naphula/Goetia-26B-A4B-v1.3",
"timestamp": "2026-06-19T08:04:47Z",
"metrics": {
"kl_divergence": 0.030937770381569862,
"refusals": 3,
"n_bad_prompts": 100
},
"parameters": {
"start_layer_index": "14",
"end_layer_index": "26",
"preserve_good_behavior_weight": "1.4404",
"steer_bad_behavior_weight": "0.0100",
"overcorrect_relative_weight": "0.9144",
"neighbor_count": "15"
},
"target_components": [
"attn.o_proj"
],
"hardware": "RTX 6000 Blackwell (96GB)"
}Run Naphula/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models