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

Johneeee/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4_58e-fp16-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-oQ4_58e-fp16-text"
Response includes
  • classification m3
  • files 14
  • author_summary 78 models
  • readme_text full
Try next
GET/models?author=Johneeee
All 78 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 2026-09-26

Metadata

Tags
mlx safetensors qwen3_5 oq quantized 4-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 402 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4e-fp16 392 Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-oQ6e 375 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4e-mtp 304
Total size
18.4 GB
Files
14
Quantizations
1
Registered
2026-09-26 09:57
Last updated on HF
2026-09-26 09:35
Source huggingface.co/Johneeee/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4_58e-fp16-text ↗

Files by quantization

Auxiliary files 14 files 18.4 GB
model-00003-of-00004.safetensors 4.69 GB 8afea3a1 download
model-00002-of-00004.safetensors 4.68 GB 36d2dee7 download
model-00001-of-00004.safetensors 4.68 GB db577d33 download
model-00004-of-00004.safetensors 4.36 GB 4b415cdc download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 178 KB 4e45f2d2 download
config.json 89.9 KB 70f2953c download
oq_imatrix_report.json 30.1 KB 327d81d3 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 381 B 213b6b9b 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-oQ4_58e-fp16-text

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

Quantization details

  • Model type: qwen3_5
  • Bits: 4
  • 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 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