← back to catalog · registered 2026-11-13 11:03

fjolsvin/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b-tiiny

fjolsvin Qwen 9B multimodal
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/fjolsvin%2FQwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b-tiiny"
Response includes
  • classification m3
  • files 14
  • benchmarks 11 entries
  • author_summary 4 models
  • readme_text full
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
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
1w ago
created 2026-11-13

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1.4 UGI
Hazardous 2.4 UGI
Natural Intelligence 17.62 UGI
Political lean -12.2% UGI
Sensitive-Info 14.65 UGI
SocPol 0.9 UGI
UGI 17.27 UGI
Willingness (10) 2.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 3 UGI
Writing 33.52 UGI

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.

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors qwen3_5 image-text-to-text finetune unsloth thinking reasoning abliterated heretic uncensored tiiny

Related

Total size
17.5 GB
Files
14
Quantizations
1
Registered
2026-11-13 11:03
Last updated on HF
2026-11-13 10:58

Files by quantization

Auxiliary files 14 files 17.5 GB
model-00001-of-00002.safetensors 9.25 GB e956a082 download
model-00002-of-00002.safetensors 8.28 GB 5b277ea9 download
tokenizer.json 12.2 MB 5f9e4d49 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 67.6 KB 5ef20ba2 download
tokenizer_config.json 8.48 KB 3e0a1107 download
chat_template.jinja 7.57 KB a585dec8 download
config.json 3.05 KB 273ce437 download
README.md 2.25 KB 56a4d1d2 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.16 KB 33818c7f download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download

README current version from Hugging Face


license: apache-2.0
language:

  • en
    pipeline_tag: image-text-to-text
    library_name: transformers
    tags:
  • finetune
  • unsloth
  • thinking
  • reasoning
  • abliterated
  • heretic
  • uncensored
  • tiiny
  • tiiny-forge
    base_model:
  • Qwen/Qwen3.5-9B
    base_model_relation: finetune

Repackaged for Tiiny Pocket import. A copy of DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b at f304bcd977ee, made by tiiny-forge so the Tiiny's Hugging Face import accepts it as a fine-tune of the store model Qwen/Qwen3.5-9B. The weights are unchanged. Changes:

  • merges.txt: copied from Qwen/Qwen3.5-9B
  • model card base_model: None -> ['Qwen/Qwen3.5-9B']

Lineage. The source card names no base model. Its norm and embedding weights are nearest to Qwen/Qwen3.5-9B (relative distance ~0.001, against ~0.003 for Qwen/Qwen3.5-9B-Base).

[DavidAU] FOLLOW | ALL MODELS | COLLECTIONS | TRENDING | FAQs | SUPPORT
| Buy Me A Coffee (😁)

[repo card updates pending]

Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b

It is really smart AND Uncensored AND has "Claude" thinking.

BENCHMARKS by Nightmedia:

         arc-c arc/e boolq hswag obkqa piqa  wino

Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b [instruct mode]
mxfp8    0.637,0.835,0.889,...

Qwen3.5-9B-Instruct
mxfp8   0.571,0.719,0.895,0.683,0.426,0.770,0.671

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.

Open in Abliteration