Get the app
← back to catalog · registered 2026-09-15 09:56

Johneeee/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-oQ6e-mtp

Johneeee 9.2B
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
75
Likes
0
Model age
1d ago
created 2026-09-15
Downloads over time
Now0→from0↑0%
00110 on Sep 150 on Sep 16Sep
Sep 15 → Sep 16 · 2 snapshots · spans 1 day

Metadata

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

Related

Other by Johneeee
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ6e-mtp 356 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4e-fp16 243 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ8e-fp16 221 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ5e-vision 220 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ6e-fp16-novision 214
Total size
7.92 GB
Files
13
Quantizations
1
Registered
2026-09-15 09:56
Last updated on HF
2026-09-15 08:57
Source huggingface.co/Johneeee/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-oQ6e-mtp ↗

Files by quantization

Auxiliary files 13 files 7.95 GB
model-00001-of-00002.safetensors 4.67 GB c98fdb5a download
model-00002-of-00002.safetensors 3.26 GB 42bc4fcf download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 118 KB a569f544 download
oq_imatrix_report.json 16.9 KB 32e9c96d download
tokenizer_config.json 14.9 KB 42659baa download
config.json 10.7 KB eae36949 download
chat_template.jinja 7.57 KB a585dec8 download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 390 B 2ea84a43 download
README.md 361 B 9f9fc941 download
generation_config.json 141 B 33c12b19 download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-oQ6e-mtp

This model was quantized using oQ (oMLX v0.6.4) mixed-precision quantization.

Quantization details

  • Model type: qwen3_5
  • Bits: 6
  • 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. 2026-09-15Upload Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-oQ6e-m...545daf2361 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 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