Get the app
← back to catalog · registered 2026-09-29 10:57

Johneeee/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-oQ5e-6target-bf16-last4native

Johneeee 27B 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Johneeee%2FQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-oQ5e-6target-bf16-last4native"
Response includes
  • classification m3
  • files 15
  • author_summary 95 models
  • readme_text full
Try next
GET/models?author=Johneeee
All 95 models by Johneeee
 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
0
Model age
today
created 2026-09-29

Metadata

Tags
mlx safetensors qwen3_5 oq quantized 5-bit region:us

Related

Other by Johneeee
Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-oQ5e 1K Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-oQ6e 467 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4e-fp16 420 Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ6e-mtp 418 Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-oQ4e-fp16 324
Total size
21.0 GB
Files
15
Quantizations
1
Registered
2026-09-29 10:57
Last updated on HF
2026-09-29 10:20
Source huggingface.co/Johneeee/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-oQ5e-6target-bf16-last4native ↗

Files by quantization

Auxiliary files 15 files 21.0 GB
model-00004-of-00005.safetensors 4.79 GB 7037166e download
model-00001-of-00005.safetensors 4.69 GB ac231fb6 download
model-00002-of-00005.safetensors 4.67 GB e1834995 download
model-00003-of-00005.safetensors 4.66 GB 4815fcef download
model-00005-of-00005.safetensors 2.14 GB ba45d5ab download
tokenizer.json 19.1 MB 6f32ce20 download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 172 KB 26ff4767 download
config.json 43.3 KB e0950c83 download
oq_imatrix_report.json 28.4 KB b86d8577 download
tokenizer_config.json 14.9 KB 5cc018ff download
chat_template.jinja 11.5 KB 82faea87 download
.gitattributes 1.53 KB 52373fe2 download
README.md 382 B 5a19e0fc download
generation_config.json 213 B d04042de download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-oQ5e-6target-bf16-last4native

This model was quantized using oQ (oMLX v0.7.0.dev4) mixed-precision quantization.

Quantization details

  • Model type: qwen3_5
  • Bits: 5
  • Group size: 64
  • Format: MLX safetensors
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