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

TheHighKage/Qwen3-30B-A3B-abliterated-erotic

TheHighKage Qwen 31B MoE
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/TheHighKage%2FQwen3-30B-A3B-abliterated-erotic"
Response includes
  • classification m1
  • files 25
  • benchmarks 16 entries
  • hub_downloads_all_time 185
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
185
19 last 30d - stable
Likes
0
Model age
7mo ago
created 2026-02-22
Downloads over time
Now186→from8↑2,225%
0681362048 on Feb 25186 on Oct 11186 on Oct 1FebAprJunAugOct
Feb 25 → Oct 11 · 72 snapshots · spans 228 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
Arena-Battles 25948 LM-Arena
LM Arena Elo 1321.1938733711484 LM-Arena
Arena-Elo-Lower 1316.3871802173958 LM-Arena
Arena-Elo-Upper 1326.0005665249007 LM-Arena
Arena-Rank 61 LM-Arena
Entertainment 1.2 UGI
Hazardous 2.9 UGI
Natural Intelligence 15.9 UGI
Political lean -26.8% UGI
Sensitive-Info 17.11 UGI
SocPol 1.4 UGI
UGI 33.07 UGI
Willingness (10) 6.5 UGI
W10-Adherence 10 UGI
W10-Direct 3 UGI
Writing 30.24 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.

Qwen/Qwen3-30B-A3B this lineage
TheHighKage/Qwen3-30B-A3B-abliterated-erotic↓ 19

Metadata

License
apache-2.0
Tags
safetensors qwen3_moe erotic explicit abliterated base_model:Qwen/Qwen3-30B-A3B base_model:finetune:Qwen/Qwen3-30B-A3B license:apache-2.0 region:us not-for-all-audiences

Related

Same base model
groxaxo/Qwen3.6-35B-A3B-Abliterated-Heretic-GGUF 2K huihui-ai/Qwen3-30B-A3B-abliterated 1K mlabonne/Qwen3-30B-A3B-abliterated 1K Ewere/Qwen3-30B-A3B-abliterated-erotic 251 Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2 149
Total size
56.9 GB
Files
25
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-02-22 07:17
Source huggingface.co/TheHighKage/Qwen3-30B-A3B-abliterated-erotic ↗ Base model Qwen/Qwen3-30B-A3B ↗

Files by quantization

Auxiliary files 25 files 56.9 GB
model-00004-of-00013.safetensors 4.65 GB 3ec5bd5d download
model-00005-of-00013.safetensors 4.65 GB 40a15b8d download
model-00006-of-00013.safetensors 4.65 GB b9d00447 download
model-00007-of-00013.safetensors 4.65 GB 1050f072 download
model-00008-of-00013.safetensors 4.65 GB 48917b01 download
model-00009-of-00013.safetensors 4.65 GB 45e29086 download
model-00010-of-00013.safetensors 4.65 GB 6345fe74 download
model-00011-of-00013.safetensors 4.65 GB 3d255621 download
model-00012-of-00013.safetensors 4.65 GB 39f59fe6 download
model-00003-of-00013.safetensors 4.65 GB 0abc6f9a download
model-00002-of-00013.safetensors 4.65 GB 234e95b8 download
model-00001-of-00013.safetensors 4.65 GB 2816a2fe download
model-00013-of-00013.safetensors 1.02 GB 4c8b6778 download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
model.safetensors.index.json 1.62 MB cb0497fa download
merges.txt 1.59 MB 31349551 download
tokenizer_config.json 9.48 KB 7345216a download
README.md 3.01 KB 5b9ab926 download
.gitattributes 1.53 KB 52373fe2 download
config.json 964 B b3b362a8 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 214 B e4f1d319 download
blank 0 B e69de29b download

README current version from Hugging Face

license: apache-2.0
base_model:

  • Qwen/Qwen3-30B-A3B
    tags:
  • erotic
  • explicit
  • abliterated

Model Card for Model ID

Qwen3-30B-A3B abliterated with erotic/explicit story prompts.

Model Details

Model Description

This is an abliterated version of Qwen/Qwen3-30B-A3B using the householder implementation provided on the repo icryo/remove-refusals-with-transformers

The harmful/harmless prompt datasets are custom built by an abliterated/quantized version of Deepsek 70B. Should have zero refusals for prompts for sexually explicit stories. Let me know if there's a sexual prompt with refusal (and please include it).

  • License: Apache 2.0
  • Finetuned from model : Qwen/Qwen3-30B-A3B

Uses

Direct Use

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Training Hyperparameters

  • Training regime: [More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Card Contact

[More Information Needed]

README history 1 version

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

  1. 2026-02-22Duplicate from Ewere/Qwen3-30B-A3B-abliterated-eroticb207f2b3 KB
    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.

Get the app Browse the catalog
Open in Abliteration