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

Dev4285/MiniArt-Uncensored

Dev4285 Qwen GGUF 33K 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/Dev4285%2FMiniArt-Uncensored"
Response includes
  • classification m-uncensored
  • files 7
  • hub_downloads_all_time 6,038
  • author_summary 1 models
  • readme_text full
Try next
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
6K
466 last 30d - cooling
Likes
1
Model age
2mo ago
created 2026-08-06
Downloads over time
Now6.2K→from1.9K↑233%
1.6K3.3K5K6.6K1.9K on Aug 56.2K on Oct 11AugSepOct
Aug 5 → Oct 11 · 50 snapshots · spans 67 days

Metadata

License
apache-2.0
Languages
en
Quantizations
Q4_K
Tags
gguf qwen2 text-generation creative roleplay lm-studio conversational en license:apache-2.0 endpoints_compatible region:us imatrix
Total size
639 MB
Files
7
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2026-08-14 12:42
Source huggingface.co/Dev4285/MiniArt-Uncensored ↗

Files by quantization

Q4_K 1 file 639 MB
MiniArt-Uncensored-Q4_K_M.gguf 639 MB 5620f67a download
Auxiliary files 6 files 11.0 KB
LICENSE 4.18 KB bcd3daa4 download
tokenizer_config.json 3.00 KB cc8a0b54 download
.gitattributes 1.55 KB 5d0a5395 download
README.md 1.43 KB 87917c94 download
Modelfile 619 B 3cea5f55 download
config.json 225 B 2656e848 download

README current version from Hugging Face

language:

  • en
    license: apache-2.0
    tags:
  • text-generation
  • gguf
  • creative
  • roleplay
  • lm-studio
  • conversational
    pipeline_tag: text-generation

MiniArt Uncensored

MiniArt Uncensored by OSAMA INC is an unrestricted version of Mini Art, optimized for local inference on Qwen2 architecture. It delivers creative conversation, storytelling, and interactive dialogue — running entirely on your own hardware.

Available in GGUF format (Q4_K_M, ~379 MB) for seamless execution across LM Studio, Ollama, llama.cpp, and KoboldCpp.

Model Overview

Property Value
Model Name MiniArt Uncensored
Made By OSAMA INC
Format GGUF (.gguf)
Quantization Q4_K_M (~379 MB)
License Apache 2.0
Context Length 32768 tokens

How to Use

LM Studio

  1. Download MiniArt-Uncensored-Q4_K_M.gguf.
  2. Open LM Studio and load the model file.
  3. Start chatting.

Ollama

ollama create miniart-uncensored -f ./Modelfile
ollama run miniart-uncensored

llama.cpp

./llama-server -m MiniArt-Uncensored-Q4_K_M.gguf -c 2048 -n 512

License

This project is licensed under the Apache 2.0 License.

README history 11 versions

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

  1. 2026-08-14Restore original MiniArt-Uncensored layout; ship single GGUF with embedded Mi...7c8622a1.4 KB
    Loading...
  2. 2026-08-14Replace model with huihui-ai/gemma-3-1b-it-abliterated; inject MiniArt Uncens...3f5329e1.4 KB
    Loading...
  3. 2026-08-10docs: update README documentation79cc2a21.4 KB
    Loading...
  4. 2026-08-10docs: remove system prompt text display from README8e13b031.4 KB
    Loading...
  5. 2026-08-10docs: update README with new system prompt and OSAMA INC identity13337393.3 KB
    Loading...
  6. 2026-08-10docs: update model file size in README01458e51.4 KB
    Loading...
  7. 2026-08-10fix: correct context length and file size in READMEec5fe4a1.4 KB
    Loading...
  8. 2026-08-07Upload README.md with huggingface_hub806e4d11.4 KB
    Loading...
  9. 2026-08-06Upload README.md with huggingface_hubc53ac151.4 KB
    Loading...
  10. 2026-08-06Upload README.md with huggingface_hub7eed8681.3 KB
    Loading...
  11. 2026-08-06Upload README.md with huggingface_hub695d16a2.6 KB
    Loading...

Discussions 1 thread

  1. 2026-08-06I must be doing something wrong.open2 💬#1
    Loading...

Continue on Hugging Face →

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