Get the app
← back to catalog · registered 2026-08-22 13:56

analogbox/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4bit

analogbox Qwen 39B second-order
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/analogbox%2FQwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4bit"
Response includes
  • classification m3
  • files 13
  • hub_downloads_all_time 1,901
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m3
Sibling qwen models · same method
 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 · lifetime
2K
142 last 30d - cooling
Likes
2
Model age
3mo ago
created 2026-06-25

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

TeichAI/claude-4.5-opus-high-reasoning-250x DavidAU/PkDick-Deckard-5-Datasets
Downloads over time
Now2K→from137↑1,329%
467441.4K2.1K137 on Jul 12K on Oct 12JulAugSepOct
Jul 1 → Oct 12 · 55 snapshots · spans 103 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking↓ 524 this lineage
analogbox/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4bit↓ 142

Metadata

License
apache-2.0
Languages
en zh
Tags
mlx safetensors qwen3_5 unsloth fine tune heretic uncensored abliterated multi-stage tuned. all use cases coder creative

Related

Same base model
DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF 193K mlx-community/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit 7K mradermacher/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-GGUF 4K mradermacher/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-i1-GGUF 2K Butzeman/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF 1K
Total size
20.5 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-25 09:03
Source huggingface.co/analogbox/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4bit ↗ Base model DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking →

Files by quantization

Auxiliary files 13 files 20.5 GB
model-00002-of-00005.safetensors 4.99 GB 7f6c5bc1 download
model-00003-of-00005.safetensors 4.98 GB edc9e491 download
model-00001-of-00005.safetensors 4.96 GB 8b9ca74f download
model-00004-of-00005.safetensors 4.88 GB 719dedca download
model-00005-of-00005.safetensors 682 MB 5806a4ed download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 278 KB edc9c0d5 download
chat_template.jinja 7.58 KB a8755d82 download
config.json 5.08 KB d46948ea download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.13 KB 8d610519 download
README.md 669 B 99eb2581 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face

language:

  • en
  • zh
    license: apache-2.0
    tags:
  • unsloth
  • fine tune
  • heretic
  • uncensored
  • abliterated
  • multi-stage tuned.
  • all use cases
  • coder
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prosing
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • mlx
    datasets:
  • TeichAI/claude-4.5-opus-high-reasoning-250x
  • DavidAU/PkDick-Deckard-5-Datasets
    pipeline_tag: text-generation
    library_name: mlx
    base_model: DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking

README history 1 version

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

  1. 2026-06-25Upload folder using huggingface_hubd038087669 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.

Get the app Browse the catalog
Open in Abliteration