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

mradermacher/Uncensored-Kybalion-3.2-1B-GGUF

mradermacher Llama 1B 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%2FUncensored-Kybalion-3.2-1B-GGUF"
Response includes
  • classification m8
  • files 14
  • hub_downloads_all_time 1,468
  • 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='NovaCorp/Uncensored-Kybalion-3.2-1B' (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
1K
262 last 30d - stable
Likes
0
Model age
5mo ago
created 2026-04-16

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now1.5K→from869↑75%
8361.1K1.3K1.6K869 on Apr 151.5K on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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 · 918 downloads combined

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

Metadata

License
llama3.2
Languages
en es
Quantizations
F16 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf uncensored abliterated low-refusals rp roleplay nsfw merge not-for-all-audiences llama continued-pretraining

Related

Total size
10.8 GB
Files
14
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-04-16 07:16

Files by quantization

F16 1 file 2.31 GB
Uncensored-Kybalion-3.2-1B.f16.gguf 2.31 GB 00f47f4c download
Q8_0 1 file 1.23 GB
Uncensored-Kybalion-3.2-1B.Q8_0.gguf 1.23 GB 84feff13 download
Q6_K 1 file 974 MB
Uncensored-Kybalion-3.2-1B.Q6_K.gguf 974 MB 36d71ae2 download
Q5_K 2 files 1.68 GB
Uncensored-Kybalion-3.2-1B.Q5_K_M.gguf 869 MB cfb093d3 download
Uncensored-Kybalion-3.2-1B.Q5_K_S.gguf 851 MB 22160b02 download
Q4_K 2 files 1.47 GB
Uncensored-Kybalion-3.2-1B.Q4_K_M.gguf 770 MB 32135872 download
Uncensored-Kybalion-3.2-1B.Q4_K_S.gguf 740 MB 803bf254 download
IQ4 1 file 714 MB
Uncensored-Kybalion-3.2-1B.IQ4_XS.gguf 714 MB 9691f185 download
Q3_K 3 files 1.92 GB
Uncensored-Kybalion-3.2-1B.Q3_K_L.gguf 699 MB 6ead6ef8 download
Uncensored-Kybalion-3.2-1B.Q3_K_M.gguf 659 MB 41929d20 download
Uncensored-Kybalion-3.2-1B.Q3_K_S.gguf 612 MB 23e0eeff download
Q2_K 1 file 554 MB
Uncensored-Kybalion-3.2-1B.Q2_K.gguf 554 MB d052325a download
Auxiliary files 2 files 6.47 KB
README.md 4.12 KB 3e5121d9 download
.gitattributes 2.35 KB ad0872c9 download

README current version from Hugging Face


base_model: NovaCorp/Uncensored-Kybalion-3.2-1B
datasets:

  • FuseAI/FuseChat-3.0-DPO-Data
  • HuggingFaceFW/fineweb-edu
  • open-web-math/open-web-math
  • bigcode/starcoderdata
  • HuggingFaceTB/cosmopedia
  • teknium/OpenHermes-2.5
  • meta-math/MetaMathQA
  • sahil2801/CodeAlpaca-20k
    language:
  • en
  • es
    library_name: transformers
    license: llama3.2
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • uncensored
  • abliterated
  • low-refusals
  • rp
  • roleplay
  • nsfw
  • merge
  • not-for-all-audiences
  • llama
  • continued-pretraining
  • sft
  • lora
  • 1b
  • math
  • code
  • education
  • small-llm

About

static quants of https://huggingface.co/NovaCorp/Uncensored-Kybalion-3.2-1B

For a convenient overview and download list, visit our model page for this model.

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Uncensored-Kybalion-3.2-1B-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 0.7
GGUF Q3_K_S 0.7
GGUF Q3_K_M 0.8 lower quality
GGUF Q3_K_L 0.8
GGUF IQ4_XS 0.8
GGUF Q4_K_S 0.9 fast, recommended
GGUF Q4_K_M 0.9 fast, recommended
GGUF Q5_K_S 1.0
GGUF Q5_K_M 1.0
GGUF Q6_K 1.1 very good quality
GGUF Q8_0 1.4 fast, best quality
GGUF f16 2.6 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. 2026-04-16auto-patch README.md9be4f704.1 KB
    Loading...
  2. 2026-04-16auto-patch README.md6968c824.2 KB
    Loading...
  3. 2026-04-16uploaded from leia4d9c982378 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