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

jrcrittenden/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-Vision-mlx-5Bit

jrcrittenden Qwen 27B 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/jrcrittenden%2FQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-Vision-mlx-5Bit"
Response includes
  • classification m3
  • files 17
  • hub_downloads_all_time 714
  • 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
714
197 last 30d - stable
Likes
0
Model age
8w ago
created 2026-08-12
Downloads over time
Now796→from461↑73%
444573701830461 on Aug 19796 on Oct 11AugSepOct
Aug 19 → Oct 11 · 48 snapshots · spans 53 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/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP↓ 1,512 this lineage
jrcrittenden/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-Vision-mlx-5Bit↓ 197

Metadata

Tags
mlx safetensors qwen3_5 vision uncensored base_model:DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP base_model:quantized:DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP 5-bit region:us

Related

Same base model
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 476K schwyzquant/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 4K schwyzquants/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 3K CodyBaz/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 3K longsesh/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 2K
Total size
18.1 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-12 22:25
Source huggingface.co/jrcrittenden/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-Vision-mlx-5Bit ↗ Base model DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP →

Files by quantization

Auxiliary files 17 files 18.1 GB
model-00003-of-00004.safetensors 5.00 GB d4396e7e download
model-00002-of-00004.safetensors 4.99 GB b0d48bd0 download
model-00001-of-00004.safetensors 4.97 GB 22cc3305 download
model-00004-of-00004.safetensors 3.12 GB 8d6dc5cf download
tokenizer.json 19.1 MB 6f32ce20 download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 213 KB 8927fcbb download
chat_template-instruct.jinja 11.6 KB 53066082 download
chat_template.jinja 11.5 KB 82faea87 download
config.json 5.10 KB 7cd8249e download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.24 KB a9eacca6 download
processor_config.json 991 B 8f29fe38 download
README.md 837 B c06f49cf download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 213 B d04042de download

README current version from Hugging Face

base_model: DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
tags: [mlx, qwen3_5, vision, uncensored]

Fable-Fusion-711 — MLX 5-bit (vision retained)

5-bit / group-size 64 affine MLX quant of
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP,
converted directly from the bf16 safetensors (no GGUF round-trip).

  • Vision tower kept at bf16 (--skip-vision) — image input works.
  • MTP head stripped (unused by mlx-lm / vllm-mlx serving).
  • Both source chat templates included (chat_template.jinja, chat_template-instruct.jinja).

Serve, e.g.: vllm-mlx serve jrcrittenden/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-Vision-mlx-5Bit --reasoning-parser qwen3

Total size: 19.4 GB.

README history 3 versions

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

  1. 2026-08-12Upload folder using huggingface_hub709299e837 B
    Loading...
  2. 2026-08-12README: vision tower is 5-bit quantized, not bf16d0b236d893 B
    Loading...
  3. 2026-08-12Upload folder using huggingface_hub3db1b80837 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