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

Stetsoncody/Llama-3.2-3B-Instruct-abliterated-GGUF

Stetsoncody Llama 3B 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/Stetsoncody%2FLlama-3.2-3B-Instruct-abliterated-GGUF"
Response includes
  • classification m8
  • files 16
  • benchmarks 21 entries
  • hub_downloads_all_time 1,318
  • author_summary 1 models
  • readme_text full
Try next
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
1K
220 last 30d - stable
Likes
0
Model age
6mo ago
created 2026-03-26
Downloads over time
Now1.3K→from273↑390%
2206281K1.4K273 on Mar 251.3K on Oct 11MarAprMayJunJulAugSepOct
Mar 25 → Oct 11 · 68 snapshots · spans 200 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 8390 LM-Arena
LM Arena Elo 1118.1163530112908 LM-Arena
Arena-Elo-Lower 1110.9097939581304 LM-Arena
Arena-Elo-Upper 1125.322912064451 LM-Arena
Arena-Rank 181 LM-Arena
BBH average 0.4202879750940459 OpenLLM-v2
IFEval instruct 0.7817745803357314 OpenLLM-v2
IFEval-Prompt 0.6968576709796673 OpenLLM-v2
MATH lvl 5 0.1555891238670695 OpenLLM-v2
MMLU-Pro 0.3194813829787234 OpenLLM-v2
Entertainment 0.5 UGI
Hazardous 0 UGI
Natural Intelligence 10.45 UGI
Political lean -1.2% UGI
Sensitive-Info 4.49 UGI
SocPol 0.7 UGI
UGI 7.16 UGI
Willingness (10) 1.2 UGI
W10-Adherence 0.5 UGI
W10-Direct 2 UGI
Writing 10.44 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-3.2-3B-Instruct this lineage
Stetsoncody/Llama-3.2-3B-Instruct-abliterated-GGUF↓ 220

Metadata

License
llama3.2
Quantizations
Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
transformers gguf abliterated uncensored base_model:meta-llama/Llama-3.2-3B-Instruct base_model:quantized:meta-llama/Llama-3.2-3B-Instruct license:llama3.2 endpoints_compatible region:us conversational

Related

Same base model
QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF 13K QuantFactory/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-GGUF 2K huihui-ai/Llama-3.2-3B-Instruct-abliterated 2K DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored 1K itsumeMario/Llama-3.2-3B-Instruct-abliterated-GGUF 323
Total size
27.7 GB
Files
16
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-03-26 05:30
Source huggingface.co/Stetsoncody/Llama-3.2-3B-Instruct-abliterated-GGUF ↗ Base model meta-llama/Llama-3.2-3B-Instruct ↗

Files by quantization

Q8_0 1 file 3.19 GB
Llama-3.2-3B-Instruct-abliterated.Q8_0.gguf 3.19 GB 0de52905 download
Q6_K 1 file 2.46 GB
Llama-3.2-3B-Instruct-abliterated.Q6_K.gguf 2.46 GB e25a296c download
Q5 2 files 4.39 GB
Llama-3.2-3B-Instruct-abliterated.Q5_1.gguf 2.28 GB db2c18fc download
Llama-3.2-3B-Instruct-abliterated.Q5_0.gguf 2.11 GB 90d3726c download
Q5_K 2 files 4.28 GB
Llama-3.2-3B-Instruct-abliterated.Q5_K_M.gguf 2.16 GB 679509e3 download
Llama-3.2-3B-Instruct-abliterated.Q5_K_S.gguf 2.11 GB baeca9e7 download
Q4 2 files 3.74 GB
Llama-3.2-3B-Instruct-abliterated.Q4_1.gguf 1.95 GB 168f0177 download
Llama-3.2-3B-Instruct-abliterated.Q4_0.gguf 1.79 GB 06912eff download
Q4_K 2 files 3.68 GB
Llama-3.2-3B-Instruct-abliterated.Q4_K_M.gguf 1.88 GB e1f2b428 download
Llama-3.2-3B-Instruct-abliterated.Q4_K_S.gguf 1.80 GB 4d89193f download
Q3_K 3 files 4.70 GB
Llama-3.2-3B-Instruct-abliterated.Q3_K_L.gguf 1.69 GB 4b986e98 download
Llama-3.2-3B-Instruct-abliterated.Q3_K_M.gguf 1.57 GB c07529c6 download
Llama-3.2-3B-Instruct-abliterated.Q3_K_S.gguf 1.44 GB 01e9ed9a download
Q2_K 1 file 1.27 GB
Llama-3.2-3B-Instruct-abliterated.Q2_K.gguf 1.27 GB 99b8f47b download
Auxiliary files 2 files 4.42 KB
.gitattributes 2.59 KB cd25ab5a download
README.md 1.83 KB 559aea6c download

README current version from Hugging Face

library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:

  • abliterated
  • uncensored

QuantFactory Banner

QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF

This is quantized version of huihui-ai/Llama-3.2-3B-Instruct-abliterated created using llama.cpp

Original Model Card

🦙 Llama-3.2-3B-Instruct-abliterated

This is an uncensored version of Llama 3.2 3B Instruct created with abliteration (see this article to know more about it).

Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.

Evaluations

The following data has been re-evaluated and calculated as the average for each test.

Benchmark Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct-abliterated
IF_Eval 76.55 76.76
MMLU Pro 27.88 28.00
TruthfulQA 50.55 50.73
BBH 41.81 41.86
GPQA 28.39 28.41

The script used for evaluation can be found inside this repository under /eval.sh, or click here

README history 1 version

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

  1. 2026-03-26Duplicate from QuantFactory/Llama-3.2-3B-Instruct-abliterated-GGUF8fcb9fa1.8 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