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

huihui-ai/Huihui-Qwen3.6-27B-abliterated

huihui-ai Qwen 28B 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/huihui-ai%2FHuihui-Qwen3.6-27B-abliterated"
Response includes
  • classification m3
  • files 29
  • benchmarks 11 entries
  • hub_downloads_all_time 74,374
  • providers 1
  • author_summary 183 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

No other method signals detected in this model.
Confidence
HIGH
Why this label 3 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=huihui-ai (specializes in M3 layer-wise ablation)
  • is_gguf=0 (base model, not repackage)
  • 'abliterated' in name/tags
Refusal direction extracted via
Extraction technique

huihui-ai layer-band extraction

Confidence
HIGH
Why we say so
producer=huihui-ai (documented layer-band methodology in model cards)
Downloads · lifetime
74K
4K last 30d - cooling
Likes
74
Descendants
44
in 39 direct forks
Model age
5mo ago
created 2026-04-23
Available via
1 provider
featherless-ai
Downloads over time
Now76.8K→from539↑14,142%
028.1K56.3K84.4K539 on Apr 2276.8K on Oct 11AprMayJunJulAugSepOct
Apr 22 → Oct 11 · 64 snapshots · spans 172 days

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 1.2 UGI
Hazardous 4.7 UGI
Natural Intelligence 33.16 UGI
Political lean -20.0% UGI
Sensitive-Info 26.98 UGI
SocPol 2.9 UGI
UGI 27.15 UGI
Willingness (10) 2.8 UGI
W10-Adherence 1.5 UGI
W10-Direct 4 UGI
Writing 42.47 UGI

Genealogy 39 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.

Qwen/Qwen3.6-27B this lineage
huihui-ai/Huihui-Qwen3.6-27B-abliterated↓ 4,286 39 forks
nbeerbower/Huihui-Qwen3.6-27B-abliterated-Athanorlite-ORPO↓ 26 2 forks
scottyjmp5/Legal-Qwen3.6-27B-Abliterated↓ 12 2 forks
hotdogs/qwen27b-abliterated-Fable-MTP↓ 240 1 fork

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5 image-text-to-text abliterated uncensored conversational base_model:Qwen/Qwen3.6-27B base_model:finetune:Qwen/Qwen3.6-27B license:apache-2.0 endpoints_compatible region:us

Related

Total size
51.7 GB
Files
29
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-23 14:23

Files by quantization

Auxiliary files 29 files 51.8 GB
model-00013-of-00015.safetensors 3.72 GB 0867aab8 download
model-00007-of-00015.safetensors 3.72 GB 1f14ce5d download
model-00001-of-00015.safetensors 3.70 GB fa762cd5 download
model-00014-of-00015.safetensors 3.67 GB 8361054c download
model-00002-of-00015.safetensors 3.65 GB 93f37141 download
model-00009-of-00015.safetensors 3.65 GB 49aec55d download
model-00011-of-00015.safetensors 3.65 GB d23eea1a download
model-00012-of-00015.safetensors 3.65 GB cc7868e8 download
model-00003-of-00015.safetensors 3.65 GB 02279bce download
model-00004-of-00015.safetensors 3.65 GB 2165e678 download
model-00010-of-00015.safetensors 3.65 GB 243b5c95 download
model-00005-of-00015.safetensors 3.65 GB 3bd4d70d download
model-00006-of-00015.safetensors 3.63 GB 75707449 download
model-00008-of-00015.safetensors 3.61 GB d86981f9 download
model-00015-of-00015.safetensors 485 MB fa8ddc72 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 110 KB ea32be69 download
tokenizer_config.json 16.3 KB 28d96ff3 download
LICENSE 11.1 KB 1d5180a4 download
chat_template.jinja 7.58 KB a8755d82 download
config.json 4.21 KB 9f3dd1b1 download
README.md 2.41 KB 5fac256e download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 202 B 023756cf download
configuration.json 51.0 B 3a6d4256 download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:

  • Qwen/Qwen3.6-27B
    tags:
  • abliterated
  • uncensored

huihui-ai/Huihui-Qwen3.6-27B-abliterated

This is an uncensored version of Qwen/Qwen3.6-27B created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

ollama

Please use the latest version of ollama

You can use huihui_ai/qwen3.6-abliterated:27b directly,

ollama run huihui_ai/qwen3.6-abliterated:27b

Usage Warnings

  • Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.

  • Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.

  • Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.

  • Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.

  • Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.

  • No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.

Donation

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
  • Support our work on Ko-fi!

README history 1 version

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

  1. 2026-04-23Super-squash branch 'main' using huggingface_hub27502c82.4 KB
    Loading...

Discussions 4 threads

  1. 2026-06-13Still seems censoredopen3 💬#4
    Loading...
  2. 2026-05-13no vision support at allclosed1 💬#3
    Loading...
  3. 2026-04-24Cite huihui on paperopen2 💬#2
    Loading...
  4. 2026-04-24Qwen3.6-27B-FP8 Can you support ablated a bit?open6 💬#1
    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.

Open in Abliteration