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

arzaan789/llama-3.1-8b-uncensored

arzaan789 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/arzaan789%2Fllama-3.1-8b-uncensored"
Response includes
  • classification m8
  • files 13
  • benchmarks 21 entries
  • hub_downloads_all_time 1,592
  • author_summary 28 models
  • readme_text full
Try next
GET/models?author=arzaan789
All 28 models by arzaan789
 GET/models?family=llama&method=m8
Sibling llama models · same method
 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)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
Why this label 3 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.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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
2K
494 last 30d - stable
Likes
0
Model age
5mo ago
created 2026-04-29
Downloads over time
Now1.7K→from329↑407%
2627751.3K1.8K329 on Apr 291.7K on Oct 11AprMayJunJulAugSepOct
Apr 29 → Oct 11 · 63 snapshots · spans 165 days

Benchmarks

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
Entertainment 0 UGI
Hazardous 0 UGI
Natural Intelligence 18.19 UGI
Political lean -15.3% UGI
Sensitive-Info 4.69 UGI
SocPol 1.4 UGI
UGI 6.46 UGI
Willingness (10) 1 UGI
W10-Adherence 0 UGI
W10-Direct 2 UGI
Writing 24.82 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.

meta-llama/Llama-3.1-8B-Instruct this lineage
arzaan789/llama-3.1-8b-uncensored↓ 494

Metadata

License
apache-2.0
Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf uncensored abliterated llama conversational text-generation base_model:meta-llama/Llama-3.1-8B-Instruct base_model:quantized:meta-llama/Llama-3.1-8B-Instruct license:apache-2.0 endpoints_compatible region:us

Related

Other by arzaan789
phi-4-mini-uncensored 1K qwen2.5-1.5b-uncensored 1K qwen2.5-3b-uncensored 1K qwen3.5-4b-uncensored 907 smolm3-3b-uncensored 878
Same base model
richardyoung/Llama-3.1-8B-Instruct-abliterated-obliteratus 739 Andycurrent/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored_GGUF 672 ccharnkij/Llama-3.1-8B-Instruct-Uncensored-GGUF 274 ApolloRaines/Llama-3.1-8B-Instruct-Uncensored-Complete 274 ApolloRaines/Llama-3.1-8B-Instruct_Abliterated 257
Total size
62.7 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-04-29 10:05
Source huggingface.co/arzaan789/llama-3.1-8b-uncensored ↗ Base model meta-llama/Llama-3.1-8B-Instruct ↗

Files by quantization

F16 1 file 15.0 GB
llama_3.1_8b_uncensored.f16.gguf 15.0 GB a39911d2 download
Q8_0 1 file 7.95 GB
llama_3.1_8b_uncensored.Q8_0.gguf 7.95 GB d13b94b6 download
Q6_K 1 file 6.14 GB
llama_3.1_8b_uncensored.Q6_K.gguf 6.14 GB f4bcd727 download
Q5_K 2 files 10.6 GB
llama_3.1_8b_uncensored.Q5_K_M.gguf 5.34 GB cd816c0d download
llama_3.1_8b_uncensored.Q5_K_S.gguf 5.21 GB 784b06dd download
Q4_K 2 files 8.95 GB
llama_3.1_8b_uncensored.Q4_K_M.gguf 4.58 GB 414008ae download
llama_3.1_8b_uncensored.Q4_K_S.gguf 4.37 GB 1c38b4a7 download
Q3_K 3 files 11.2 GB
llama_3.1_8b_uncensored.Q3_K_L.gguf 4.03 GB f01d4846 download
llama_3.1_8b_uncensored.Q3_K_M.gguf 3.74 GB 0d4dfabc download
llama_3.1_8b_uncensored.Q3_K_S.gguf 3.41 GB a387955f download
Q2_K 1 file 2.96 GB
llama_3.1_8b_uncensored.Q2_K.gguf 2.96 GB e18c01b9 download
Auxiliary files 2 files 3.54 KB
.gitattributes 2.25 KB 0de2b558 download
README.md 1.30 KB fc2e47e4 download

README current version from Hugging Face

license: apache-2.0
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:

  • uncensored
  • abliterated
  • gguf
  • llama
  • conversational
    pipeline_tag: text-generation

llama-3.1-8b-uncensored

Uncensored variant of meta-llama/Llama-3.1-8B-Instruct.

Method

  1. Abliteration (strength=0.2) — refusal direction removed from all layers
  2. LoRA fine-tune on Guilherme34/uncensor (2 epochs, r=16, alpha=32)
  3. Re-abliteration (strength=0.35) — stronger pass to remove residual refusals

Eval Results

Split Refused
Harmful (64 prompts) 3/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m llama_3.1_8b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model meta-llama/Llama-3.1-8B-Instruct
Fine-tune Dataset Guilherme34/uncensor
Epochs 2
LoRA r 16
LoRA alpha 32
Learning Rate 0.0002
Abliteration Strength 0.2
Re-abliteration Strength 0.35

Credits

README history 1 version

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

  1. 2026-04-29Upload README.md with huggingface_hub45524271.3 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