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

mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF

mradermacher Llama 8B 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/mradermacher%2FDarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF"
Response includes
  • classification m8
  • files 17
  • hub_downloads_all_time 45,683
  • author_summary 3324 models
  • readme_text full
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
HIGH
Inherited from base model
Why this label 3 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=mradermacher (M8 quantization producer, never originator)
  • is_gguf=1
  • base_model='aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored' (base has 'abliterated' marker, assume M1 default)
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
46K
2K last 30d - cooling
Likes
20
Model age
2.2y ago
created 2024-07-27
Downloads over time
Now46.4K→from510↑8,990%
017K34K50.9K510 on Jul 24, 202446.4K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 162 snapshots · spans 809 days

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.

Variants by this author 2 formats · 5K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
llama3.1
Languages
en de fr it pt hi es th zh ko ja
Quantizations
F16 IQ3 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf roleplay llama3 sillytavern idol facebook meta pytorch llama llama-3 en

Related

Total size
77.1 GB
Files
17
Quantizations
10
Registered
2026-08-22 13:56
Last updated on HF
2024-07-28 03:04

Files by quantization

F16 1 file 15.0 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.f16.gguf 15.0 GB eac97cd0 download
Q8_0 1 file 7.95 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q8_0.gguf 7.95 GB 9ad16d0a download
Q6_K 1 file 6.14 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q6_K.gguf 6.14 GB f7d76ed7 download
Q5_K 2 files 10.6 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q5_K_M.gguf 5.34 GB 9e40d346 download
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q5_K_S.gguf 5.21 GB a19c441e download
Q4_K 2 files 8.95 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q4_K_M.gguf 4.58 GB 9bf89099 download
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q4_K_S.gguf 4.37 GB 5a4e2859 download
IQ4 1 file 4.18 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.IQ4_XS.gguf 4.18 GB 0ca50e0a download
Q3_K 3 files 11.2 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q3_K_L.gguf 4.03 GB 122c08f3 download
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q3_K_M.gguf 3.74 GB fb978b9f download
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q3_K_S.gguf 3.41 GB 42136d12 download
IQ3 3 files 10.2 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.IQ3_M.gguf 3.52 GB 4fa2fc83 download
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.IQ3_S.gguf 3.43 GB 921819ac download
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.IQ3_XS.gguf 3.28 GB 5c016326 download
Q2_K 1 file 2.96 GB
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.Q2_K.gguf 2.96 GB 3b7807b5 download
Auxiliary files 2 files 7.71 KB
README.md 4.86 KB 3fb5b140 download
.gitattributes 2.85 KB 48dd3df7 download

README current version from Hugging Face


base_model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
extra_gated_fields:
Affiliation: text
Country: country
Date of birth: date_picker
First Name: text
Job title:
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
type: select
Last Name: text
language:

  • en
  • de
  • fr
  • it
  • pt
  • hi
  • es
  • th
  • zh
  • ko
  • ja
    library_name: transformers
    license: llama3.1
    quantized_by: mradermacher
    tags:
  • roleplay
  • llama3
  • sillytavern
  • idol
  • facebook
  • meta
  • pytorch
  • llama
  • llama-3

About

static quants of https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored

weighted/imatrix quants are available at https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs
for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF Q2_K 3.3
GGUF IQ3_XS 3.6
GGUF Q3_K_S 3.8
GGUF IQ3_S 3.8 beats Q3_K*
GGUF IQ3_M 3.9
GGUF Q3_K_M 4.1 lower quality
GGUF Q3_K_L 4.4
GGUF IQ4_XS 4.6
GGUF Q4_K_S 4.8 fast, recommended
GGUF Q4_K_M 5.0 fast, recommended
GGUF Q5_K_S 5.7
GGUF Q5_K_M 5.8
GGUF Q6_K 6.7 very good quality
GGUF Q8_0 8.6 fast, best quality
GGUF f16 16.2 16 bpw, overkill

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

README history 3 versions

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

  1. 2024-07-28auto-patch README.md8990d0f4.9 KB
    Loading...
  2. 2024-07-27auto-patch README.md09055645 KB
    Loading...
  3. 2024-07-27uploaded from nethype/leiac2fe8b3247 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.

Open in Abliteration