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

huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated-FP8

huihui-ai Qwen 8B 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-VL-8B-Instruct-abliterated-FP8"
Response includes
  • classification m3
  • files 3
  • benchmarks 11 entries
  • author_summary 184 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 · 30-day
0
Likes
9
Model age
3mo ago
created 2026-06-23
Downloads over time
Now0→from0↑0%
00110 on Jun 240 on Sep 26JunJulAugSep
Jun 24 → Sep 26 · 40 snapshots · spans 94 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 4.1 UGI
Natural Intelligence 17.46 UGI
Political lean -18.5% UGI
Sensitive-Info 19.17 UGI
SocPol 1.1 UGI
UGI 32.78 UGI
Willingness (10) 6 UGI
W10-Adherence 6 UGI
W10-Direct 6 UGI
Writing 30.31 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.

Variants by this author 2 formats · 33K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Tags
transformers safetensors abliterated uncensored image-text-to-text base_model:Qwen/Qwen3-VL-8B-Instruct base_model:finetune:Qwen/Qwen3-VL-8B-Instruct license:apache-2.0 endpoints_compatible region:us

Related

Total size
8.18 GB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-24 01:21

Files by quantization

Auxiliary files 3 files 8.18 GB
model.safetensors 8.18 GB 53eed2b0 download
README.md 2.25 KB deb50091 download
.gitattributes 1.48 KB a6344aac download

README current version from Hugging Face


license: apache-2.0
base_model:

  • Qwen/Qwen3-VL-8B-Instruct
    pipeline_tag: image-text-to-text
    tags:
  • abliterated
  • uncensored
    library_name: transformers

huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated-FP8

This is the FP8 version of huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated;

This model can replace ideogram-ai/ideogram-4-fp8's text_encoder, which should remove some constraints.

It was only the text part that was processed, not the image part.

Usage

Simply overwrite the model.safetensors file inside ideogram-ai/ideogram-4-fp8's text_encoder with the one from this model.

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 3 versions

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

  1. 2026-06-24Update README.md73ef8192.2 KB
    Loading...
  2. 2026-06-23Update README.md9ab7eaa2.2 KB
    Loading...
  3. 2026-06-23Create README.mddde11e82.1 KB
    Loading...

Discussions 3 threads

  1. 2026-08-22config.json and other needed files?open1 💬#3
    Loading...
  2. 2026-08-21Ты умеешь генерировать картинка?closed2 💬#2
    Loading...
  3. 2026-06-24thank you, after i try it with comfyui it is not workingopen7 💬#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