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

LWDCLS/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF-IQ-Imatrix-Request

LWDCLS Llama 8B GGUF 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/LWDCLS%2FDarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF-IQ-Imatrix-Request"
Response includes
  • classification m-uncensored
  • files 15
  • hub_downloads_all_time 19,773
  • author_summary 9 models
  • readme_text full
Try next
GET/models?author=LWDCLS
All 9 models by LWDCLS
 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
20K
553 last 30d - cooling
Likes
12
Model age
2.2y ago
created 2024-07-25
Downloads over time
Now20K→from2.3K↑781%
07.3K14.6K21.9K2.3K on Jul 24, 202420K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

License
unlicense
Quantizations
BF16 F16 Q4_K Q5_K
Tags
gguf license:unlicense endpoints_compatible region:us conversational

Related

Other by LWDCLS
llama3-8B-DarkIdol-2.1-Uncensored-1048K-GGUF-IQ-Imatrix-Request 2K DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-GGUF-IQ-Imatrix-Request 2K llama3-8B-DarkIdol-2.3-Uncensored-32K-GGUF-IQ-Imatrix-Request 1K DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF-IQ-Imatrix-Request 705 Phi-4-mini-instruct-abliterated-GGUF-IQ-Imatrix-Request 465
Total size
74.3 GB
Files
15
Quantizations
5
Registered
2026-08-22 13:56
Last updated on HF
2024-07-25 01:31
Source huggingface.co/LWDCLS/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF-IQ-Imatrix-Request ↗

Files by quantization

BF16 1 file 15.0 GB
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-BF16.gguf 15.0 GB a4170d05 download
F16 1 file 15.0 GB
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-F16.gguf 15.0 GB c4de2ea4 download
Q5_K 2 files 10.6 GB
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-Q5_K_M-imat.gguf 5.34 GB 83279c87 download
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-Q5_K_S-imat.gguf 5.21 GB 7182a0b7 download
Q4_K 2 files 8.95 GB
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-Q4_K_M-imat.gguf 4.58 GB 7c96924d download
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-Q4_K_S-imat.gguf 4.37 GB 7b5e937c download
Auxiliary files 9 files 24.8 GB
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-Q8_0-imat.gguf 7.95 GB b8cbce74 download
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-Q6_K-imat.gguf 6.14 GB d1e84802 download
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-IQ4_XS-imat.gguf 4.14 GB 49e0f7b3 download
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-IQ3_M-imat.gguf 3.52 GB 97ce1f1d download
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-IQ3_XXS-imat.gguf 3.05 GB 7fb23431 download
imatrix.dat 4.76 MB c5e6c3c9 download
imatrix-with-rp-ex.txt 222 KB 6269bf7d download
.gitattributes 2.58 KB fb43acba download
README.md 347 B 944f1569 download

README current version from Hugging Face

README history 2 versions

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

  1. 2024-07-25Update README.mdb6bf01d347 B
    Loading...
  2. 2024-07-25initial commitec2342027 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