← back to catalog · registered 2026-09-24 17:57

mradermacher/ThinkingCap-Qwen3.8-27B-Uncensored-Heretic-GGUF

mradermacher 27B GGUF
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/mradermacher%2FThinkingCap-Qwen3.8-27B-Uncensored-Heretic-GGUF"
Response includes
  • classification m3
  • files 6
  • author_summary 3254 models
  • readme_text full
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
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-24

Metadata

Quantizations
Q2_K Q4_K
Tags
transformers gguf qwen3_8 token-efficient efficient-thinking heretic uncensored decensored abliterated en base_model:OS-Software/ThinkingCap-Qwen3.8-27B-Uncensored-Heretic base_model:quantized:OS-Software/ThinkingCap-Qwen3.8-27B-Uncensored-Heretic

Related

Total size
24.5 GB
Files
6
Quantizations
5
Registered
2026-09-24 17:57
Last updated on HF
2026-09-24 18:46

Files by quantization

Q4_K 1 file 14.5 GB
ThinkingCap-Qwen3.8-27B-Uncensored-Heretic.Q4_K_S.gguf 14.5 GB b3bc4428 download
Q2_K 1 file 9.98 GB
ThinkingCap-Qwen3.8-27B-Uncensored-Heretic.Q2_K.gguf 9.98 GB e98b5806 download
F16 1 file 885 MB
ThinkingCap-Qwen3.8-27B-Uncensored-Heretic.mmproj-f16.gguf 885 MB 21f35cd1 download
Q8_0 1 file 600 MB
ThinkingCap-Qwen3.8-27B-Uncensored-Heretic.mmproj-Q8_0.gguf 600 MB 69ad8827 download
Auxiliary files 2 files 2.23 KB
.gitattributes 1.85 KB 2dd57fb6 download
README.md 397 B 404213e4 download

README current version from Hugging Face

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.