← back to catalog · registered 2026-09-30 06:58

Johneeee/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ5-fa6-qkv6-tail6-e6-b8

Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Johneeee%2FQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ5-fa6-qkv6-tail6-e6-b8"
Response includes
  • classification m3
  • files 14
  • author_summary 110 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
22
Likes
0
Model age
7w ago
created 2026-09-30
Downloads over time
Now 19 → from 0 ↑ 0%
071421 0 on Sep 30 19 on Oct 2 SepOct
Sep 30 → Oct 2 · 3 snapshots · spans 2 days

Metadata

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

Related

Total size
20.1 GB
Files
14
Quantizations
1
Registered
2026-09-30 06:58
Last updated on HF
2026-09-30 06:11

Files by quantization

Auxiliary files 14 files 20.2 GB
model-00004-of-00005.safetensors 4.67 GB e988e0b6 download
model-00003-of-00005.safetensors 4.66 GB 1072f20d download
model-00001-of-00005.safetensors 4.66 GB f583ea2f download
model-00002-of-00005.safetensors 4.66 GB dc5c1672 download
model-00005-of-00005.safetensors 1.48 GB 52ce9a09 download
tokenizer.json 19.1 MB 6f32ce20 download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 178 KB 9b488043 download
config.json 79.0 KB cb83ebf5 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 373 B d26640d9 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-oQ5-fa6-qkv6-tail6-e6-b8

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

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-30 Upload Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ5-fa6-qkv6-ta... 64e9d4f 373 B
    Loading...
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.

Open in Abliteration