Get the app
← back to catalog · registered 2026-09-27 15:57

Johneeee/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-fp16-oQ6e-g128-text

Johneeee 27B 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Johneeee%2FQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-fp16-oQ6e-g128-text"
Response includes
  • classification m3
  • files 15
  • author_summary 82 models
  • readme_text full
Try next
GET/models?author=Johneeee
All 82 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 2026-09-27

Metadata

Tags
mlx safetensors qwen3_5 oq quantized 6-bit region:us

Related

Other by Johneeee
Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-oQ5e 1K Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ6e-mtp 412 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4e-fp16 403 Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-oQ6e 396 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4e-mtp 308
Total size
20.0 GB
Files
15
Quantizations
1
Registered
2026-09-27 15:57
Last updated on HF
2026-09-27 15:45
Source huggingface.co/Johneeee/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-fp16-oQ6e-g128-text ↗

Files by quantization

Auxiliary files 15 files 20.0 GB
model-00003-of-00005.safetensors 4.69 GB ff39deac download
model-00001-of-00005.safetensors 4.68 GB d795d610 download
model-00004-of-00005.safetensors 4.68 GB 94e91bf8 download
model-00002-of-00005.safetensors 4.66 GB c9d870e9 download
model-00005-of-00005.safetensors 1.24 GB 70c17be9 download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 178 KB 179dbfa2 download
oq_imatrix_report.json 30.1 KB 7f715efb download
config.json 18.7 KB 1d946487 download
tokenizer_config.json 16.0 KB 08f41ce2 download
chat_template.jinja 8.74 KB 5a39aa2b download
.gitattributes 1.53 KB 52373fe2 download
README.md 384 B 36ac8c34 download
generation_config.json 213 B d04042de download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-fp16-oQ6e-g128-text

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

Quantization details

  • Model type: qwen3_5
  • Bits: 6
  • Group size: 128
  • 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