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

m-i/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-mlx

m-i Qwen 40B 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%2FQwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-mlx"
Response includes
  • classification m3
  • files 27
  • hub_downloads_all_time 808
  • 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
808
154 last 30d - stable
Likes
0
Model age
2mo ago
created 2026-08-10
Downloads over time
Now860→from0↑0%
03156319460 on Aug 5860 on Oct 12AugSepOct
Aug 5 → Oct 12 · 51 snapshots · spans 68 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-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored↓ 335 this lineage
m-i/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-mlx↓ 154

Metadata

License
apache-2.0
Languages
en zh
Tags
mlx safetensors qwen3_5 MTP fine tune heretic uncensored abliterated multi-stage tuned. all use cases thinking reasoning

Related

Other by m-i
Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-mxfp8 31 QwQ-32B-abliterated-mlx-8Bit 17
Same base model
DavidAU/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-NM-DAU-NEO-MAX-MTP-GGUF 9K goldhub/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-W4A16-AutoRound 176
Total size
73.6 GB
Files
27
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-10 11:53
Source huggingface.co/m-i/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-mlx ↗ Base model DavidAU/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored →

Files by quantization

Auxiliary files 27 files 73.7 GB
model-00013-of-00015.safetensors 4.98 GB a9b55a50 download
model-00009-of-00015.safetensors 4.98 GB d3bd4b79 download
model-00005-of-00015.safetensors 4.98 GB 8eac27f4 download
model-00007-of-00015.safetensors 4.96 GB eee874be download
model-00012-of-00015.safetensors 4.96 GB 9affcb5c download
model-00004-of-00015.safetensors 4.96 GB 3648e81e download
model-00006-of-00015.safetensors 4.96 GB 9ceb2263 download
model-00014-of-00015.safetensors 4.96 GB fdaf1c7c download
model-00010-of-00015.safetensors 4.96 GB 9393bc79 download
model-00011-of-00015.safetensors 4.96 GB 5a976686 download
model-00008-of-00015.safetensors 4.96 GB 200cec1d download
model-00003-of-00015.safetensors 4.96 GB e5f0da2c download
model-00002-of-00015.safetensors 4.96 GB 996573d5 download
model-00001-of-00015.safetensors 4.87 GB 90e9cefc download
model-00015-of-00015.safetensors 4.27 GB 0a2ac1e1 download
tokenizer.json 19.1 MB 06b95093 download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 156 KB 86c0798f download
chat_template.jinja 11.5 KB 82faea87 download
config.json 5.76 KB d4e266cb download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.14 KB 1d134cd2 download
README.md 1.13 KB 5d8f4e18 download
processor_config.json 991 B 8f29fe38 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face

language:

  • en
  • zh
    license: apache-2.0
    tags:
  • MTP
  • fine tune
  • heretic
  • uncensored
  • abliterated
  • multi-stage tuned.
  • all use cases
  • thinking
  • reasoning
  • qwen3.6
  • coder
  • creative
  • writing
  • fiction
  • roleplaying
  • bfloat16
  • mlx
    pipeline_tag: image-text-to-text
    base_model: DavidAU/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored
    library_name: mlx

m-i/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-mlx

This model was converted to MLX format from DavidAU/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored
using mlx-vlm version 0.6.10.
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/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-mlx --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. 2026-08-10Upload folder using huggingface_hub32b6b5a1.1 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