Get the app
← back to catalog · registered 2026-09-17 10:56

Johneeee/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-oQ5e

Johneeee 9B
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 2026-09-17

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 360 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ4e-fp16 257 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ8e-fp16 239 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ5e-vision 223 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-oQ6e-fp16-novision 221
Total size
5.94 GB
Files
12
Quantizations
1
Registered
2026-09-17 10:56
Last updated on HF
2026-09-17 10:14
Source huggingface.co/Johneeee/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-oQ5e ↗

Files by quantization

Auxiliary files 12 files 5.97 GB
model-00001-of-00002.safetensors 4.66 GB 7b42c4ca download
model-00002-of-00002.safetensors 1.28 GB b8e2f59a download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 89.2 KB f5091a1d download
oq_imatrix_report.json 16.6 KB 2675af61 download
config.json 8.03 KB 08018943 download
chat_template.jinja 7.61 KB 04dbb310 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.11 KB a068e246 download
README.md 355 B e28b6fbf download
generation_config.json 115 B affcdf18 download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-oQ5e

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