Get the app
← back to catalog · registered 2026-09-18 14:56

Johneeee/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-oQ5e-fp16

Johneeee 27B 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Johneeee%2FQwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-oQ5e-fp16"
Response includes
  • classification m3
  • files 14
  • author_summary 46 models
  • readme_text full
Try next
GET/models?author=Johneeee
All 46 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 2026-09-18

Variants by this author 2 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

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

Related

Other by Johneeee
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ6e-mtp 366 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4e-fp16 279 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ8e-fp16 262 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ5e-vision 238 Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-oQ6e-novision 236
Total size
17.8 GB
Files
14
Quantizations
1
Registered
2026-09-18 14:56
Last updated on HF
2026-09-18 14:26
Source huggingface.co/Johneeee/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-oQ5e-fp16 ↗

Files by quantization

Auxiliary files 14 files 17.9 GB
model-00001-of-00004.safetensors 4.70 GB 9136b499 download
model-00003-of-00004.safetensors 4.66 GB 6571a4b4 download
model-00002-of-00004.safetensors 4.66 GB fe3df26d download
model-00004-of-00004.safetensors 3.83 GB 9aac628b download
tokenizer.json 12.2 MB 0997f410 download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 178 KB bd9853e5 download
oq_imatrix_report.json 30.2 KB 852e9538 download
chat_template.jinja 16.7 KB 6e25105d download
config.json 14.6 KB 05f6a418 download
tokenizer_config.json 8.48 KB 1a7e62d0 download
.gitattributes 1.53 KB 52373fe2 download
README.md 373 B f1eafb74 download
generation_config.json 213 B d04042de download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized

Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored-oQ5e-fp16

This model was quantized using oQ (oMLX v0.7.0.dev2) 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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.

See supported apps Browse the catalog