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

ccharnkij/Llama-3.1-8B-Instruct-Uncensored-GGUF

ccharnkij 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/ccharnkij%2FLlama-3.1-8B-Instruct-Uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 7
  • benchmarks 21 entries
  • hub_downloads_all_time 2,411
  • author_summary 20 models
  • readme_text full
Try next
GET/models?author=ccharnkij
All 20 models by ccharnkij
 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
2K
274 last 30d - stable
Likes
1
Model age
7mo ago
created 2026-03-13
Downloads over time
Now2.5K→from52↑4,704%
09141.8K2.7K52 on Mar 112.5K on Oct 112.5K on Oct 9MarAprMayJunJulAugSepOct
Mar 11 → Oct 11 · 70 snapshots · spans 214 days

Benchmarks

Benchmark Score Source
Entertainment 1.2 UGI
Hazardous 2.4 UGI
Natural Intelligence 17.07 UGI
Political lean -2.2% UGI
Sensitive-Info 16.12 UGI
SocPol 1.6 UGI
UGI 35.75 UGI
Willingness (10) 7.5 UGI
W10-Adherence 8 UGI
W10-Direct 7 UGI
Writing 25.1 UGI
Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Arena-Battles 52578 LM-Arena
LM Arena Elo 1193.5124798763727 LM-Arena
Arena-Elo-Lower 1189.790314040387 LM-Arena
Arena-Elo-Upper 1197.234645712358 LM-Arena
Arena-Rank 148 LM-Arena
BBH average 0.4671163575042159 OpenLLM-v2
IFEval instruct 0.564748201438849 OpenLLM-v2
IFEval-Prompt 0.4195933456561922 OpenLLM-v2
MATH lvl 5 0.15407854984894256 OpenLLM-v2
MMLU-Pro 0.37982047872340424 OpenLLM-v2

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.

meta-llama/Llama-3.1-8B-Instruct this lineage
ccharnkij/Llama-3.1-8B-Instruct-Uncensored-GGUF↓ 274

Variants by this author 2 formats · 357 downloads combined

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

Metadata

License
llama3.1
Languages
en
Quantizations
F16 Q4_K Q5_K Q6_K Q8_0
Tags
gguf llama llama-3 llama-3.1 uncensored text-generation en base_model:meta-llama/Llama-3.1-8B-Instruct base_model:quantized:meta-llama/Llama-3.1-8B-Instruct license:llama3.1 endpoints_compatible region:us

Related

Other by ccharnkij
Qwen3.5-9B-Uncensored-GGUF 3K Ministral-3-14B-Reasoning-2512-Uncensored-GGUF 2K gpt-oss-120b-Uncensored-GGUF 636 Gemma-4-E4B-it-Uncensored-GGUF 555 gemma-4-31B-it-Uncensored-GGUF 546
Same base model
richardyoung/Llama-3.1-8B-Instruct-abliterated-obliteratus 739 Andycurrent/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored_GGUF 672 arzaan789/llama-3.1-8b-uncensored 494 ApolloRaines/Llama-3.1-8B-Instruct-Uncensored-Complete 274 ApolloRaines/Llama-3.1-8B-Instruct_Abliterated 257
Total size
39.0 GB
Files
7
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2026-06-08 01:40
Source huggingface.co/ccharnkij/Llama-3.1-8B-Instruct-Uncensored-GGUF ↗ Base model meta-llama/Llama-3.1-8B-Instruct ↗

Files by quantization

F16 1 file 15.0 GB
Llama-3.1-8B-Instruct-Uncensored-f16.gguf 15.0 GB 5c24e469 download
Q8_0 1 file 7.95 GB
Llama-3.1-8B-Instruct-Uncensored-Q8_0.gguf 7.95 GB 1e549853 download
Q6_K 1 file 6.14 GB
Llama-3.1-8B-Instruct-Uncensored-Q6_K.gguf 6.14 GB eed4823a download
Q5_K 1 file 5.34 GB
Llama-3.1-8B-Instruct-Uncensored-Q5_K_M.gguf 5.34 GB f7c26cb4 download
Q4_K 1 file 4.58 GB
Llama-3.1-8B-Instruct-Uncensored-Q4_K_M.gguf 4.58 GB 3562b905 download
Auxiliary files 2 files 2.97 KB
.gitattributes 1.87 KB 9d032c37 download
README.md 1.09 KB 5ba145cc download

README current version from Hugging Face

license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:

  • llama
  • llama-3
  • llama-3.1
  • uncensored
  • text-generation
  • gguf
    language:
  • en
    pipeline_tag: text-generation

Llama-3.1-8B-Uncensored-GGUF

GGUF quantized versions of Llama-3.1-8B-Uncensored, a fine-tuned version of Meta Llama 3.1 8B Instruct with uncensored responses.

For the full precision safetensors version, see 👉 Llama-3.1-8B-Uncensored

💬 Feedback

If you use this model, I'd love to hear from you! Feel free to:

  • Leave a comment on this model page
  • Open a discussion for questions or suggestions
  • Report any issues or unexpected behaviors

Your feedback helps improve future versions.

⚠️ Disclaimer

This model is intended for research and educational purposes only.

License

This model is licensed under the Meta Llama 3.1 Community License.

README history 3 versions

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

  1. 2026-06-08Update README.md5327d871.1 KB
    Loading...
  2. 2026-03-13Upload folder using huggingface_hubcffa9e1862 B
    Loading...
  3. 2026-03-13initial commite2d992a26 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