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

mradermacher/Uncensored-Jordan-33B-i1-GGUF

mradermacher 33B GGUF second-order 2K 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-Jordan-33B-i1-GGUF"
Response includes
  • classification m8
  • files 25
  • hub_downloads_all_time 9,059
  • 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='ajibawa-2023/Uncensored-Jordan-33B' (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
9K
704 last 30d - cooling
Likes
1
Model age
2.5y ago
created 2024-03-30
Downloads over time
Now9.3K→from498↑1,763%
03.4K6.8K10.2K498 on Jul 24, 20249.3K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 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 · 1K downloads combined

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

Metadata

Languages
en
Quantizations
IQ1 IQ2 IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K
Tags
transformers gguf en base_model:ajibawa-2023/Uncensored-Jordan-33B base_model:quantized:ajibawa-2023/Uncensored-Jordan-33B license:cc-by-nc-nd-4.0 endpoints_compatible region:us

Related

Total size
315 GB
Files
25
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-05-06 05:34

Files by quantization

Q6_K 1 file 25.1 GB
Uncensored-Jordan-33B.i1-Q6_K.gguf 25.1 GB 9709b234 download
Q5_K 2 files 42.8 GB
Uncensored-Jordan-33B.i1-Q5_K_M.gguf 21.7 GB 6193701f download
Uncensored-Jordan-33B.i1-Q5_K_S.gguf 21.1 GB ce3d0b8d download
Q4_K 2 files 36.0 GB
Uncensored-Jordan-33B.i1-Q4_K_M.gguf 18.5 GB 1f332948 download
Uncensored-Jordan-33B.i1-Q4_K_S.gguf 17.4 GB 0b77e0c6 download
Q4 1 file 17.4 GB
Uncensored-Jordan-33B.i1-Q4_0.gguf 17.4 GB 7bec6d6e download
IQ4 2 files 33.7 GB
Uncensored-Jordan-33B.i1-IQ4_NL.gguf 17.3 GB 2ce9c663 download
Uncensored-Jordan-33B.i1-IQ4_XS.gguf 16.4 GB fbfeb353 download
Q3_K 3 files 44.6 GB
Uncensored-Jordan-33B.i1-Q3_K_L.gguf 16.3 GB 2c788597 download
Uncensored-Jordan-33B.i1-Q3_K_M.gguf 14.9 GB ba18b86e download
Uncensored-Jordan-33B.i1-Q3_K_S.gguf 13.3 GB 5fedad41 download
IQ3 4 files 51.8 GB
Uncensored-Jordan-33B.i1-IQ3_M.gguf 14.1 GB 2e37f351 download
Uncensored-Jordan-33B.i1-IQ3_S.gguf 13.3 GB cc1f7361 download
Uncensored-Jordan-33B.i1-IQ3_XS.gguf 12.6 GB 1657c1ca download
Uncensored-Jordan-33B.i1-IQ3_XXS.gguf 11.7 GB 9cc36ad9 download
Q2_K 1 file 11.5 GB
Uncensored-Jordan-33B.i1-Q2_K.gguf 11.5 GB f8c7ba5f download
IQ2 4 files 38.3 GB
Uncensored-Jordan-33B.i1-IQ2_M.gguf 10.7 GB a43ba4b3 download
Uncensored-Jordan-33B.i1-IQ2_S.gguf 9.93 GB b2fa64c8 download
Uncensored-Jordan-33B.i1-IQ2_XS.gguf 9.23 GB 19c32486 download
Uncensored-Jordan-33B.i1-IQ2_XXS.gguf 8.40 GB 5d4135c4 download
IQ1 2 files 14.3 GB
Uncensored-Jordan-33B.i1-IQ1_M.gguf 7.46 GB 4e8db40c download
Uncensored-Jordan-33B.i1-IQ1_S.gguf 6.89 GB e25193d1 download
Auxiliary files 3 files 13.3 MB
imatrix.dat 13.3 MB 24078dad download
README.md 4.84 KB 399f1c68 download
.gitattributes 3.09 KB 675831af download

README current version from Hugging Face


base_model: ajibawa-2023/Uncensored-Jordan-33B
language:

  • en
    library_name: transformers
    license: cc-by-nc-nd-4.0
    quantized_by: mradermacher

About

weighted/imatrix quants of https://huggingface.co/ajibawa-2023/Uncensored-Jordan-33B

static quants are available at https://huggingface.co/mradermacher/Uncensored-Jordan-33B-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 i1-IQ1_S 7.5 for the desperate
GGUF i1-IQ1_M 8.1 mostly desperate
GGUF i1-IQ2_XXS 9.1
GGUF i1-IQ2_XS 10.0
GGUF i1-IQ2_S 10.8
GGUF i1-IQ2_M 11.6
GGUF i1-Q2_K 12.4 IQ3_XXS probably better
GGUF i1-IQ3_XXS 12.7 lower quality
GGUF i1-IQ3_XS 13.7
GGUF i1-IQ3_S 14.4 beats Q3_K*
GGUF i1-Q3_K_S 14.4 IQ3_XS probably better
GGUF i1-IQ3_M 15.2
GGUF i1-Q3_K_M 16.1 IQ3_S probably better
GGUF i1-Q3_K_L 17.6 IQ3_M probably better
GGUF i1-IQ4_XS 17.7
GGUF i1-IQ4_NL 18.7 prefer IQ4_XS
GGUF i1-Q4_0 18.8 fast, low quality
GGUF i1-Q4_K_S 18.8 optimal size/speed/quality
GGUF i1-Q4_K_M 20.0 fast, recommended
GGUF i1-Q5_K_S 22.7
GGUF i1-Q5_K_M 23.4
GGUF i1-Q6_K 27.0 practically like static Q6_K

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 6 versions

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

  1. 2024-05-06auto-patch README.md620ef1f4.8 KB
    Loading...
  2. 2024-04-27auto-patch README.md30fc7d84.9 KB
    Loading...
  3. 2024-03-30auto-patch README.md0e7f1034.7 KB
    Loading...
  4. 2024-03-30auto-patch README.mdc1b717e4.7 KB
    Loading...
  5. 2024-03-30auto-patch README.md37dc5a44.7 KB
    Loading...
  6. 2024-03-30uploaded from nethype/db1d65cf4e85 B
    Loading...

Discussions 1 thread

  1. 2024-04-06Many problems with this AI - pretty much uselessclosed2 💬#1
    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