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

filvyb/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF

filvyb Qwen 9B GGUF multimodal second-order 262K ctx
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/filvyb%2FQwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF"
Response includes
  • classification m3
  • files 6
  • hub_downloads_all_time 16,094
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=filvyb
All 3 models by filvyb
 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
16K
859 last 30d - cooling
Likes
8
Model age
4mo ago
created 2026-05-21
Downloads over time
Now16.4K→from600↑2,638%
06K12K18K600 on May 2016.4K on Oct 11MayJunJulAugSepOct
May 20 → Oct 11 · 62 snapshots · spans 144 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/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness↓ 517 this lineage
filvyb/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF↓ 859

Metadata

License
apache-2.0
Languages
en zh
Quantizations
BF16
Tags
transformers gguf unsloth heretic uncensored abliterated fine tune creative creative writing fiction writing plot generation sub-plot generation

Related

Other by filvyb
Huihui-Step3-VL-10B-abliterated-GGUF 2K Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED 954
Same base model
Blasserman/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF 2K Uwes1980/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF 475 KryptykAngel/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF 473 KW-KI/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q5_K_M-GGUF 0 KW-KI/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF 0
Total size
16.1 GB
Files
6
Quantizations
4
Registered
2026-08-22 13:56
Last updated on HF
2026-05-22 11:20
Source huggingface.co/filvyb/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF ↗ Base model DavidAU/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness →

Files by quantization

BF16 2 files 17.0 GB
Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-BF16.gguf 16.1 GB b691cc0a download
mmproj-Qwen3.6-9b-Heretic-Uncensored-Thinking-Sweet-Madness-BF16.gguf 888 MB 29aa617b download
F16 1 file 885 MB
mmproj-Qwen3.6-9b-Heretic-Uncensored-Thinking-Sweet-Madness-F16.gguf 885 MB f0c7bea0 download
Q8_0 1 file 600 MB
mmproj-Qwen3.6-9b-Heretic-Uncensored-Thinking-Sweet-Madness-Q8_0.gguf 600 MB 7915e23e download
Auxiliary files 2 files 2.58 KB
.gitattributes 1.89 KB ee8f5b27 download
README.md 707 B 325350f4 download

README current version from Hugging Face

language:

  • en
  • zh
    license: apache-2.0
    tags:
  • unsloth
  • heretic
  • uncensored
  • abliterated
  • fine tune
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • fiction writing
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prosing
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • all use cases
    library_name: transformers
    pipeline_tag: image-text-to-text
    base_model:
  • DavidAU/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness

This is a GGUF of DavidAU/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness

README history 3 versions

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

  1. 2026-05-21Update README.mde406bbf707 B
    Loading...
  2. 2026-05-21Update README.md1f9db74731 B
    Loading...
  3. 2026-05-21initial commit0864f8828 B
    Loading...

Discussions 1 thread

  1. 2026-05-23Is the model good for agentic tasks ?open2 💬#1
    Loading...

Continue on Hugging Face →

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