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

arthur25346/Llama-3.2-Abliterated-Aqua-Star-AMD

arthur25346 Llama GGUF
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/arthur25346%2FLlama-3.2-Abliterated-Aqua-Star-AMD"
Response includes
  • classification m8
  • files 5
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=arthur25346
All 2 models by arthur25346
 GET/models?family=llama&method=m8
Sibling llama models · same method
 GET/methods/m8
What "m8" means · taxonomy
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
M1 Direct removal →
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
How we label → About M8 →
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 · 30-day
14
↑ 645% in 90 days
Likes
1
Model age
8mo ago
created 2026-02-11
Downloads over time
Now216→from29↑645%
209116323529 on Feb 11216 on Sep 2216 on Aug 19FebMarAprMayJunJulAugSep
Feb 11 → Sep 2 · 35 snapshots · spans 203 days

Metadata

License
other
Quantizations
Q3_K
Tags
gguf endpoints_compatible region:us conversational

Related

Other by arthur25346
Uncensored-GPT-20B-OSS_Claude-Opus-4.5 0
Total size
1.57 GB
Files
5
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2026-02-11 09:30
Source huggingface.co/arthur25346/Llama-3.2-Abliterated-Aqua-Star-AMD ↗

Files by quantization

Q3_K 1 file 1.57 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K_M.gguf 1.57 GB 0d9aed6b download
Auxiliary files 4 files 3.77 KB
.gitattributes 1.66 KB 1b8ff602 download
app.py 1.09 KB eac52998 download
README.md 1015 B 524ced1d download
requirements.txt 39.0 B 8cb0b4eb download

README current version from Hugging Face

title: Richard's Abliterated AI
emoji: 🧠
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: 5.0.0
app_file: app.py
pinned: false
license: other
tags:

  • uncensored
  • abliterated
  • gguf
  • amd-optimized
  • richard-erkhov

🔓 Richard's Abliterated AI (GGUF)

This Space features an uncensored/abliterated model curated by Richard Erkhov. It is optimized for efficiency and designed to provide direct answers without moralizing or refusal filters.

🛠️ Configuration

  • Model Curator: Richard Erkhov
  • Format: GGUF (Highly compressed & fast)
  • Hardware: Optimized for AMD GPUs via ROCm/HIPBlas
  • Nature: Non-Chinese, Small, and Smart

🚀 Running on AMD Hardware

If you plan to run this model on your local AMD machine, make sure you have ROCm installed. To enable AMD support, set the following CMake argument and install the llama-cpp-python package:

export CMAKE_ARGS="-DGGML_HIPBLAS=ON"
pip install llama-cpp-python

README history 4 versions

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

  1. 2026-02-11Update README.mde61ae5b1015 B
    Loading...
  2. 2026-02-11Update README.mde5d301a1.1 KB
    Loading...
  3. 2026-02-11Update README.md05a1d08132 B
    Loading...
  4. 2026-02-11initial commit8a96cba28 B
    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