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

rodrigomt/Qwen3.5-27B-Uncensored-Aggressive

rodrigomt 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/rodrigomt%2FQwen3.5-27B-Uncensored-Aggressive"
Response includes
  • classification m-uncensored
  • files 23
  • benchmarks 11 entries
  • hub_downloads_all_time 310
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=rodrigomt
All 2 models by rodrigomt
 GET/models?family=qwen&method=m-uncensored
Sibling qwen models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
310
20 last 30d - cooling
Likes
0
Descendants
2
in 2 direct forks
Model age
6mo ago
created 2026-04-12
Downloads over time
Now319→from219↑46%
214252291329219 on Apr 15319 on Oct 11319 on Oct 10AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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 UGI
Hazardous 1.8 UGI
Natural Intelligence 35.83 UGI
Political lean -17.8% UGI
Sensitive-Info 17.72 UGI
SocPol 2.7 UGI
UGI 15.98 UGI
Willingness (10) 1.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 1 UGI
Writing 42.37 UGI

Genealogy 2 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/Qwen3.5-27B this lineage
rodrigomt/Qwen3.5-27B-Uncensored-Aggressive↓ 20 2 forks
mradermacher/Qwen3.5-27B-Uncensored-Aggressive-i1-GGUF↓ 903
mradermacher/Qwen3.5-27B-Uncensored-Aggressive-GGUF↓ 439

Metadata

License
other
Languages
multilingual
Tags
safetensors qwen3_5 qwen qwen3.5 uncensored multimodal image-text-to-text conversational multilingual base_model:Qwen/Qwen3.5-27B base_model:finetune:Qwen/Qwen3.5-27B license:other

Related

Other by rodrigomt
Qwen3.5-4B-Uncensored-Aggressive 2K
Same base model
huihui-ai/Huihui-Qwen3.5-27B-abliterated 137K LiconStudio/Qwen3.5-27B-abliterated-GGUF 4K backpropSukuna/Qwen3.5-27B-Instruct-Uncensored 2K SpaceTimee/Suri-Qwen-3.5-27B-Uncensored-GGUF 883 llmfan46/Qwen3.5-27B-ultra-uncensored-heretic-v1 577
Total size
51.7 GB
Files
23
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-14 04:24
Source huggingface.co/rodrigomt/Qwen3.5-27B-Uncensored-Aggressive ↗ Base model Qwen/Qwen3.5-27B ↗

Files by quantization

Auxiliary files 23 files 51.8 GB
model.safetensors-00008-of-00011.safetensors 5.00 GB 59af8650 download
model.safetensors-00010-of-00011.safetensors 4.98 GB 09b7a241 download
model.safetensors-00009-of-00011.safetensors 4.98 GB 5ab910b3 download
model.safetensors-00004-of-00011.safetensors 4.98 GB 05369918 download
model.safetensors-00003-of-00011.safetensors 4.98 GB 11a2434b download
model.safetensors-00005-of-00011.safetensors 4.98 GB b90110c4 download
model.safetensors-00006-of-00011.safetensors 4.98 GB e41f6bc3 download
model.safetensors-00007-of-00011.safetensors 4.98 GB 3cfbc5a1 download
model.safetensors-00002-of-00011.safetensors 4.98 GB 78e23f6a download
model.safetensors-00001-of-00011.safetensors 4.90 GB 2d737fda download
model.safetensors-00011-of-00011.safetensors 2.00 GB dab7c6c5 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 124 KB 95d45893 download
tokenizer_config.json 16.3 KB eda48d3e download
chat_template.jinja 7.57 KB a585dec8 download
config.json 4.04 KB bde2be7f download
README.md 1.62 KB 1a186c07 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 244 B 85b45ab4 download

README current version from Hugging Face

license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE
language:

  • multilingual
    pipeline_tag: image-text-to-text
    tags:
  • qwen
  • qwen3.5
  • uncensored
  • safetensors
  • multimodal
    base_model:
  • Qwen/Qwen3.5-27B

Qwen3.5-27B-Uncensored-HauhauCS-Aggressive (Safetensors)

safetensors conversion of HauhauCS/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive GGUF release.

This repository contains raw Hugging Face / Transformers weights converted from GGUF for direct use with transformers, vLLM, SGLang, and other runtimes that support safetensors.

Summary

  • Aggressive uncensored variant with refusal removal
  • Sharded weights across 11 safetensors files (model.safetensors-00001-of-00011.safetensors … model.safetensors-00011-of-00011.safetensors)
  • Multimodal architecture with text, image, and video support
  • Native context length of 262144 tokens

Files

  • config.json
  • model.safetensors.index.json
  • model.safetensors-00001-of-00011.safetensors … model.safetensors-00011-of-00011.safetensors
  • tokenizer.json
  • tokenizer_config.json
  • merges.txt
  • vocab.json
  • preprocessor_config.json
  • video_preprocessor_config.json
  • chat_template.jinja
  • generation_config.json

Notes

  • This repository does not include GGUF files or an mmproj file: the weights here are already in raw safetensors format
  • The source was a GGUF release; this repository exists to distribute a Hugging Face-compatible conversion
  • Use a recent stack, since Qwen3.5 support is still new across some runtimes

README history 7 versions

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

  1. 2026-04-14Update README.md14d57091.6 KB
    Loading...
  2. 2026-04-12Update README.md55756301.6 KB
    Loading...
  3. 2026-04-12Add source repo link to README6bfc7fc1.6 KB
    Loading...
  4. 2026-04-12Update README.md311d3151.5 KB
    Loading...
  5. 2026-04-12Update README.mde1f85bd1.6 KB
    Loading...
  6. 2026-04-12Add YAML metadata to README48694b11.6 KB
    Loading...
  7. 2026-04-12Upload Qwen3.5-27B-Uncensored-HauhauCS-Aggressive safetensorsf61868e1.3 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