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

m-i/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-mxfp8

m-i Qwen 39B multimodal 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/m-i%2FQwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-mxfp8"
Response includes
  • classification m3
  • files 19
  • hub_downloads_all_time 1,443
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=m-i
All 3 models by m-i
 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
1K
31 last 30d - cooling
Likes
0
Model age
6mo ago
created 2026-04-01

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
Now1.5K→from1.2K↑26%
1.1K1.3K1.4K1.5K1.2K on Apr 151.5K on Oct 111.5K on Oct 8AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking↓ 87 this lineage
m-i/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-mxfp8↓ 31

Metadata

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

Related

Other by m-i
Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-mlx 156 QwQ-32B-abliterated-mlx-8Bit 17
Same base model
mradermacher/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking-i1-GGUF 2K mradermacher/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking-GGUF 585 DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking 270 DavidAU/Qwen3.5-21B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking 159 Bercraft/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking-Q8_0-GGUF 149
Total size
38.4 GB
Files
19
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-01 19:15
Source huggingface.co/m-i/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-mxfp8 ↗ Base model DavidAU/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking →

Files by quantization

Auxiliary files 19 files 38.4 GB
model-00002-of-00008.safetensors 4.95 GB b90c0430 download
model-00006-of-00008.safetensors 4.94 GB c16b9b84 download
model-00004-of-00008.safetensors 4.94 GB 3de54725 download
model-00003-of-00008.safetensors 4.93 GB 4b7be1fa download
model-00005-of-00008.safetensors 4.93 GB 85d829a3 download
model-00007-of-00008.safetensors 4.93 GB 6e936ba5 download
model-00001-of-00008.safetensors 4.92 GB a29fec8c download
model-00008-of-00008.safetensors 3.86 GB 7b095553 download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 231 KB e0d3d6b6 download
chat_template.jinja 7.78 KB 5a663a52 download
config.json 5.41 KB fddceb1b download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.30 KB 5499e00e download
processor_config.json 1.29 KB 266ebfa0 download
tokenizer_config.json 1.07 KB e15d4cc3 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 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
    base_model:
  • DavidAU/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking
    pipeline_tag: image-text-to-text
    library_name: transformers

m-i/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-mxfp8

This model was converted to MLX format from DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking using mlx-vlm version 0.4.0.
Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model m-i/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-mxfp8 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

README history 1 version

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

  1. 2026-04-01Upload folder using huggingface_hub9d399a11.3 KB
    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