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

RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf

RichardErkhov 8B GGUF 8K 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/RichardErkhov%2Fsaishf_-_Aura-Uncensored-OAS-8B-L3-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 5,769
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 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)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 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.
  • author=richarderkhov (M8 quantization producer)
  • is_gguf=1
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 · lifetime
6K
664 last 30d - stable
Likes
1
Model age
2.0y ago
created 2024-10-08
Downloads over time
Now5.9K→from0↑0%
02.2K4.3K6.5K0 on Oct 2, 20245.9K on Oct 12Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 2, 2024 → Oct 12 · 146 snapshots · spans 740 days

Metadata

Quantizations
IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
gguf arxiv:2403.19522 endpoints_compatible region:us conversational

Related

Other by RichardErkhov
byroneverson_-_gemma-2-27b-it-abliterated-gguf 2K huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf 2K failspy_-_Codestral-22B-v0.1-abliterated-v3-gguf 2K Rupesh2_-_Llama-3.1-8B-Uncensored-gguf 2K huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf 2K
Total size
100 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-10-08 11:28
Source huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf ↗

Files by quantization

Q8_0 1 file 7.95 GB
Aura-Uncensored-OAS-8B-L3.Q8_0.gguf 7.95 GB 597326ca download
Q6_K 1 file 6.14 GB
Aura-Uncensored-OAS-8B-L3.Q6_K.gguf 6.14 GB b83a9832 download
Q5 2 files 10.9 GB
Aura-Uncensored-OAS-8B-L3.Q5_1.gguf 5.65 GB a7da765b download
Aura-Uncensored-OAS-8B-L3.Q5_0.gguf 5.21 GB 7be8e9e7 download
Q5_K 3 files 15.9 GB
Aura-Uncensored-OAS-8B-L3.Q5_K.gguf 5.34 GB a52cb929 download
Aura-Uncensored-OAS-8B-L3.Q5_K_M.gguf 5.34 GB a52cb929 download
Aura-Uncensored-OAS-8B-L3.Q5_K_S.gguf 5.21 GB df78fde1 download
Q4 2 files 9.12 GB
Aura-Uncensored-OAS-8B-L3.Q4_1.gguf 4.78 GB 3cf5bac3 download
Aura-Uncensored-OAS-8B-L3.Q4_0.gguf 4.34 GB c0ca1e48 download
Q4_K 3 files 13.5 GB
Aura-Uncensored-OAS-8B-L3.Q4_K.gguf 4.58 GB c0c5f9a6 download
Aura-Uncensored-OAS-8B-L3.Q4_K_M.gguf 4.58 GB c0c5f9a6 download
Aura-Uncensored-OAS-8B-L3.Q4_K_S.gguf 4.37 GB 03e5c585 download
IQ4 2 files 8.56 GB
Aura-Uncensored-OAS-8B-L3.IQ4_NL.gguf 4.38 GB 41c5c939 download
Aura-Uncensored-OAS-8B-L3.IQ4_XS.gguf 4.18 GB 3df69edd download
Q3_K 4 files 14.9 GB
Aura-Uncensored-OAS-8B-L3.Q3_K_L.gguf 4.03 GB 3bbe8e9a download
Aura-Uncensored-OAS-8B-L3.Q3_K.gguf 3.74 GB ac25c2e8 download
Aura-Uncensored-OAS-8B-L3.Q3_K_M.gguf 3.74 GB ac25c2e8 download
Aura-Uncensored-OAS-8B-L3.Q3_K_S.gguf 3.41 GB 96488c10 download
IQ3 3 files 10.2 GB
Aura-Uncensored-OAS-8B-L3.IQ3_M.gguf 3.52 GB 1adda169 download
Aura-Uncensored-OAS-8B-L3.IQ3_S.gguf 3.43 GB 10827ca8 download
Aura-Uncensored-OAS-8B-L3.IQ3_XS.gguf 3.28 GB 2941e7fa download
Q2_K 1 file 2.96 GB
Aura-Uncensored-OAS-8B-L3.Q2_K.gguf 2.96 GB 0c5d7212 download
Auxiliary files 2 files 10.1 KB
README.md 7.05 KB d5aafb48 download
.gitattributes 3.05 KB 0d036154 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Aura-Uncensored-OAS-8B-L3 - GGUF

Name Quant method Size
Aura-Uncensored-OAS-8B-L3.Q2_K.gguf Q2_K 2.96GB
Aura-Uncensored-OAS-8B-L3.IQ3_XS.gguf IQ3_XS 3.28GB
Aura-Uncensored-OAS-8B-L3.IQ3_S.gguf IQ3_S 3.43GB
Aura-Uncensored-OAS-8B-L3.Q3_K_S.gguf Q3_K_S 3.41GB
Aura-Uncensored-OAS-8B-L3.IQ3_M.gguf IQ3_M 3.52GB
Aura-Uncensored-OAS-8B-L3.Q3_K.gguf Q3_K 3.74GB
Aura-Uncensored-OAS-8B-L3.Q3_K_M.gguf Q3_K_M 3.74GB
Aura-Uncensored-OAS-8B-L3.Q3_K_L.gguf Q3_K_L 4.03GB
Aura-Uncensored-OAS-8B-L3.IQ4_XS.gguf IQ4_XS 4.18GB
Aura-Uncensored-OAS-8B-L3.Q4_0.gguf Q4_0 4.34GB
Aura-Uncensored-OAS-8B-L3.IQ4_NL.gguf IQ4_NL 4.38GB
Aura-Uncensored-OAS-8B-L3.Q4_K_S.gguf Q4_K_S 4.37GB
Aura-Uncensored-OAS-8B-L3.Q4_K.gguf Q4_K 4.58GB
Aura-Uncensored-OAS-8B-L3.Q4_K_M.gguf Q4_K_M 4.58GB
Aura-Uncensored-OAS-8B-L3.Q4_1.gguf Q4_1 4.78GB
Aura-Uncensored-OAS-8B-L3.Q5_0.gguf Q5_0 5.21GB
Aura-Uncensored-OAS-8B-L3.Q5_K_S.gguf Q5_K_S 5.21GB
Aura-Uncensored-OAS-8B-L3.Q5_K.gguf Q5_K 5.34GB
Aura-Uncensored-OAS-8B-L3.Q5_K_M.gguf Q5_K_M 5.34GB
Aura-Uncensored-OAS-8B-L3.Q5_1.gguf Q5_1 5.65GB
Aura-Uncensored-OAS-8B-L3.Q6_K.gguf Q6_K 6.14GB
Aura-Uncensored-OAS-8B-L3.Q8_0.gguf Q8_0 7.95GB

Original model description:

license: cc-by-nc-4.0
base_model:

  • Undi95/Llama3-Unholy-8B-OAS
  • ResplendentAI/Theory_of_Mind_Llama3
  • Undi95/Llama3-Unholy-8B-OAS
  • ResplendentAI/Luna_Llama3
  • Undi95/Llama3-Unholy-8B-OAS
  • Undi95/Llama3-Unholy-8B-OAS
  • ResplendentAI/Aura_Llama3
  • Undi95/Llama3-Unholy-8B-OAS
  • ResplendentAI/BlueMoon_Llama3
  • Undi95/Llama3-Unholy-8B-OAS
  • ResplendentAI/RP_Format_QuoteAsterisk_Llama3
    library_name: transformers
    tags:
  • mergekit
  • merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

This is a rerun of ResplendentAI/Aura_Uncensored_l3_8B using Undi95/Llama3-Unholy-8B-OAS instead of Undi95/Llama-3-Unholy-8B in the hopes it will result in a less censored, uncensored aura.

Merge Method

This model was merged using the Model Stock merge method using Undi95/Llama3-Unholy-8B-OAS as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/Theory_of_Mind_Llama3
  - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/Aura_Llama3
  - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/Luna_Llama3
  - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/BlueMoon_Llama3
  - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/RP_Format_QuoteAsterisk_Llama3
merge_method: model_stock
base_model: Undi95/Llama3-Unholy-8B-OAS
dtype: float16

README history 1 version

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

  1. 2024-10-08uploaded readmeef6be3f7 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