Get the app
← back to catalog · registered 2026-11-03 09:02

DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Lightside

DavidAU Qwen 27B multimodal
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/DavidAU%2FQwen3.8-27B-Ultimate-Heretic-Uncensored-Lightside"
Response includes
  • classification m3
  • files 24
  • author_summary 227 models
  • readme_text full
Try next
GET/models?author=DavidAU
All 227 models by DavidAU
 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 2026-11-03

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
DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Lightside

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors qwen3_5 image-text-to-text heretic qwen3_8 qwen3_6 uncensored abliterated finetune Cold Fusion GAIN Training

Related

Other by DavidAU
Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 2M Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 1.4M Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 418K Qwen3-8B-64k-Context-2X-Josiefied-Uncensored 132K Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF 109K
Same base model
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF 3.4M JonathanColetti/Qwen3.8-27B-Uncensored-GGUF 2.6M HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF 2.4M 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF 1.1M azukivc/Qwen3.8-27B-Uncensored-GGUF 148K

Control vectors

Vectors for this model →
alesha-pro/Qwen3.8-27B-Persona-v2-GGUF 1 discodamone/golden-gate-qwen 1
Total size
51.7 GB
Files
24
Quantizations
1
Registered
2026-11-03 09:02
Last updated on HF
2026-11-03 08:07
Source huggingface.co/DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Lightside ↗ Base model Qwen/Qwen3.8-27B ↗

Files by quantization

Auxiliary files 24 files 51.8 GB
model-00003-of-00012.safetensors 4.62 GB ******** download
model-00005-of-00012.safetensors 4.62 GB ******** download
model-00007-of-00012.safetensors 4.62 GB ******** download
model-00009-of-00012.safetensors 4.62 GB ******** download
model-00008-of-00012.safetensors 4.59 GB ******** download
model-00010-of-00012.safetensors 4.59 GB ******** download
model-00004-of-00012.safetensors 4.59 GB ******** download
model-00006-of-00012.safetensors 4.57 GB ******** download
model-00011-of-00012.safetensors 4.57 GB ******** download
model-00002-of-00012.safetensors 4.51 GB ******** download
model-00012-of-00012.safetensors 3.34 GB ******** download
model-00001-of-00012.safetensors 2.37 GB ******** download
model-mtp-restored.safetensors 100 MB ******** download
tokenizer.json 12.2 MB ******** download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 111 KB 490712ba download
chat_template.jinja 8.74 KB c0c686f9 download
tokenizer_config.json 8.48 KB 1a7e62d0 download
config.json 3.71 KB 51b4a29a download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.03 KB 95514e45 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face

license: apache-2.0
language:

  • en
    pipeline_tag: image-text-to-text
    library_name: transformers
    tags:
  • heretic
  • qwen3_8
  • qwen3_6
  • uncensored
  • heretic
  • abliterated
  • finetune
  • Cold Fusion
  • GAIN Training
  • Multi-stage tuning
  • all use cases
  • unsloth
  • 27 reasoning modes
  • 27 instruct modes
  • 15 AI Constructs
  • 5 Super AI Constructs
  • Brainstorm AI Construct
  • Brainstorm Business AI Construct
  • Universal Teacher AI Construct
  • Agent AI Construct
  • Coder AI Construct
  • Turbo-Brilliance
  • 9 Xhigh reasoning modes
  • unsloth
  • fine tune
  • multi-stage tuned
  • thinking
  • reasoning
  • all use cases
  • coder
  • creative
  • creative writing
  • all genres
  • story
  • writing
  • fiction
  • roleplaying
  • bfloat16
  • all use cases
    base_model:
  • Qwen/Qwen3.8-27B

[RELEASING: Nov 6; FINALIZING with Turbo Brilliance V2 (50x+) ; two versions to be released: "Heretic", and "Heretic-Light" ; GGUFs pending]

Lighter Version ("Lightside" heretic) of this project:

https://huggingface.co/DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored

Releasing shortly...

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 Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration