Get the app
← back to catalog · registered 2026-09-26 09:57

DarkRomeo88/Qwen3.8-27B-uncensored-heretic-w4a8-ComfyUI

DarkRomeo88 Qwen 27B 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/DarkRomeo88%2FQwen3.8-27B-uncensored-heretic-w4a8-ComfyUI"
Response includes
  • classification m3
  • files 3
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m3
Sibling qwen models · same method
 GET/methods/m3
What "m3" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · 30-day
0
Likes
1
Model age
today
created 2026-09-26

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Qwen/Qwen3.8-27B this lineage
DarkRomeo88/Qwen3.8-27B-uncensored-heretic-w4a8-ComfyUI

Metadata

License
apache-2.0
Tags
comfyui heretic text_encoder uncesored qwen3.8 qwen base_model:Qwen/Qwen3.8-27B base_model:finetune:Qwen/Qwen3.8-27B license:apache-2.0 region:us

Related

Same base model
JonathanColetti/Qwen3.8-27B-Uncensored-GGUF 2.3M huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF 2.2M HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF 2.1M 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF 1.5M orcarouter/Qwen3.8-27B-Uncensored-FP8 234K
Total size
20.2 GB
Files
3
Quantizations
1
Registered
2026-09-26 09:57
Last updated on HF
2026-09-26 09:49
Source huggingface.co/DarkRomeo88/Qwen3.8-27B-uncensored-heretic-w4a8-ComfyUI ↗ Base model Qwen/Qwen3.8-27B ↗

Files by quantization

Auxiliary files 3 files 20.2 GB
qwen3.8_27b_uncensored_heretic_w4a8_convrot.safetensors 20.2 GB 1d066534 download
.gitattributes 1.48 KB a6344aac download
README.md 429 B cae5ab2d download

README current version from Hugging Face

license: apache-2.0
base_model:

  • Qwen/Qwen3.8-27B
  • heretic-org/Qwen3.8-27B-heretic-ara
    tags:
  • comfyui
  • heretic
  • text_encoder
  • uncesored
  • qwen3.8
  • qwen

Repacked Qwen3.8-27B-UNCENSORED-Heretic — W4A8 ConvRot for ComfyUI

Only used for text generation and image description.

put in Comfyui/models/text_encoders/

load it with CLIPLoader and prompt generation through ComfyUI's Generate Text node.

Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in app" button that hands off directly to a local runtime of your choice - Abliteration, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.

See supported apps Browse the catalog