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

Anubis136/Llama-3.2-3b-NSFW_Aesir_Uncensored-GGUF

Anubis136 Llama 3B GGUF second-order 131K 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/Anubis136%2FLlama-3.2-3b-NSFW_Aesir_Uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 4
  • benchmarks 11 entries
  • hub_downloads_all_time 2,515
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=llama&method=m-uncensored
Sibling llama 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
3K
459 last 30d - stable
Likes
1
Model age
4mo ago
created 2026-06-07

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

MinervaAI/Aesir-Preview
Downloads over time
Now2.6K→from443↑498%
3331.2K2K2.9K443 on Jun 102.6K on Oct 11JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 days

Benchmarks

Benchmark Score Source
Entertainment 1.4 UGI
Hazardous 0 UGI
Natural Intelligence 9.95 UGI
Political lean 2.4% UGI
Sensitive-Info 8.5 UGI
SocPol 0.8 UGI
UGI 21.5 UGI
Willingness (10) 4.8 UGI
W10-Adherence 3.5 UGI
W10-Direct 6 UGI
Writing 22.13 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.

chuanli11/Llama-3.2-3B-Instruct-uncensored↓ 600 this lineage
Anubis136/Llama-3.2-3b-NSFW_Aesir_Uncensored-GGUF↓ 459

Metadata

License
apache-2.0
Languages
en es
Tags
transformers gguf llama-cpp koboldcpp rp roleplay nsfw uncensored not-for-all-audiences en es dataset:MinervaAI/Aesir-Preview

Related

Same base model
bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF 48K mradermacher/Llama-3.2-3B-Instruct-uncensored-GGUF 4K hungng/Llama-3.2-uncensored-erotica 3K mradermacher/Llama-3.2-3B-Instruct-uncensored-i1-GGUF 3K PurpleAILAB/Llama-3.2-3B-Instruct-uncensored-LoRA_final-Q4_K_M-GGUF 2K
Total size
1.90 GB
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-07 18:53
Source huggingface.co/Anubis136/Llama-3.2-3b-NSFW_Aesir_Uncensored-GGUF ↗ Base model chuanli11/Llama-3.2-3B-Instruct-uncensored →

Files by quantization

Auxiliary files 4 files 1.90 GB
Llama-3.2-3b-NSFW_Aesir_Uncensored.gguf 1.90 GB cd5fdd9c download
imatrix.dat 2.85 MB ac64f811 download
.gitattributes 1.69 KB c232e198 download
README.md 944 B 9503f9ef download

README current version from Hugging Face

library_name: transformers
tags:

  • llama-cpp
  • koboldcpp
  • rp
  • roleplay
  • nsfw
  • uncensored
  • not-for-all-audiences
    base_model: chuanli11/Llama-3.2-3B-Instruct-uncensored
    license: apache-2.0
    datasets:
  • MinervaAI/Aesir-Preview
    language:
  • en
  • es
    metrics:
  • accuracy

LLAMA 3.2 3B NSFW AESIR UNCENSORED GGUF
Note: At the moment this is going to be the only model that I plan to upload from more than 2 trillion parameters since I am only interested in focusing on small models.

Created for an evaluative purpose in quantization Q4_XS to make it lighter, this model is the result of combining the Llama 3.2 model with MinervaAI's Aesir Preview dataset intended for roleplay games.

I don't know at the moment the quality of the result, although it should be good due to the number of parameters.

As for the RAM required to make it run smoothly, I guess that it will require more than 3gb of RAM. If you have less than that, forget it.

README history 2 versions

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

  1. 2026-06-07Update README.mde9be850944 B
    Loading...
  2. 2026-06-07Duplicate from Novaciano/Llama-3.2-3b-NSFW_Aesir_Uncensored-GGUF807b413954 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