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

kraven1109/Step3-VL-10B-GGUF-abliterated

kraven1109 10B GGUF 66K 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/kraven1109%2FStep3-VL-10B-GGUF-abliterated"
Response includes
  • classification m8
  • files 5
  • hub_downloads_all_time 1,179
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
1K
87 last 30d - cooling
Likes
2
Model age
7mo ago
created 2026-02-23
Downloads over time
Now1.2K→from150↑700%
985009031.3K150 on Feb 251.2K on Oct 111.2K on Oct 10FebAprJunAugOct
Feb 25 → Oct 11 · 72 snapshots · spans 228 days

Metadata

Quantizations
Q6_K
Tags
gguf endpoints_compatible region:us conversational
Total size
6.26 GB
Files
5
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-02-23 03:01

Files by quantization

Q6_K 1 file 6.26 GB
Huihui-Step3-VL-10B-abliterated-Q6_K.gguf 6.26 GB 96837a4a download
F16 1 file 3.70 GB
step3vl-mmproj-f16.gguf 3.70 GB 44fd1342 download
Auxiliary files 3 files 20.4 MB
llama-cuda13-Step3-VL-support.7z 20.4 MB 83859d8c download
README.md 1.68 KB 519391ff download
.gitattributes 1.62 KB 1734b879 download

README current version from Hugging Face

This model is GGUF version converted from huihui-ai/Huihui-Step3-VL-10B-abliterated
This is an uncensored version of stepfun-ai/Step3-VL-10B created with abliteration (see remove-refusals-with-transformers to know more about it).

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

The abliterated model will no longer say "I can’t describe or analyze this image."

Please use it with responsibility, this is disclamer from original 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.

README history 1 version

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

  1. 2026-02-23Create README.md1b625331.7 KB
    Loading...

Discussions 1 thread

  1. 2026-03-15Step3-VL llama.cpp supportopen1 💬#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