← back to catalog · registered 2026-09-29 14:58

QWEasd250342/huihui-ai_Qwen3-14B-abliterated-GGUF

QWEasd250342 14B GGUF second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/QWEasd250342%2Fhuihui-ai_Qwen3-14B-abliterated-GGUF"
Response includes
  • classification m-uncensored
  • files 29
  • author_summary 1 models
  • readme_text full
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
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 · 30-day
0
Likes
0
Model age
today
created 2026-09-29

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.

Metadata

License
apache-2.0
Quantizations
BF16 IQ2 IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K Q8_0
Tags
gguf chat abliterated uncensored text-generation base_model:huihui-ai/Qwen3-14B-abliterated base_model:quantized:huihui-ai/Qwen3-14B-abliterated license:apache-2.0 endpoints_compatible region:us

Related

Total size
224 GB
Files
29
Quantizations
12
Registered
2026-09-29 14:58
Last updated on HF
2026-09-29 14:01

Files by quantization

BF16 1 file 27.5 GB
huihui-ai_Qwen3-14B-abliterated-bf16.gguf 27.5 GB c9e5ea7b download
Q8_0 1 file 14.6 GB
huihui-ai_Qwen3-14B-abliterated-Q8_0.gguf 14.6 GB 905faf80 download
Q6_K 2 files 22.9 GB
huihui-ai_Qwen3-14B-abliterated-Q6_K_L.gguf 11.6 GB 5bf1a37b download
huihui-ai_Qwen3-14B-abliterated-Q6_K.gguf 11.3 GB d449c727 download
Q5_K 3 files 29.6 GB
huihui-ai_Qwen3-14B-abliterated-Q5_K_L.gguf 10.2 GB 1f9ed0a6 download
huihui-ai_Qwen3-14B-abliterated-Q5_K_M.gguf 9.79 GB 736734da download
huihui-ai_Qwen3-14B-abliterated-Q5_K_S.gguf 9.56 GB 8b005ce5 download
Q4_K 3 files 25.3 GB
huihui-ai_Qwen3-14B-abliterated-Q4_K_L.gguf 8.92 GB 04fb64d0 download
huihui-ai_Qwen3-14B-abliterated-Q4_K_M.gguf 8.38 GB d7688905 download
huihui-ai_Qwen3-14B-abliterated-Q4_K_S.gguf 7.98 GB 5bbedee9 download
Q4 2 files 16.7 GB
huihui-ai_Qwen3-14B-abliterated-Q4_1.gguf 8.74 GB 70eb4af4 download
huihui-ai_Qwen3-14B-abliterated-Q4_0.gguf 7.96 GB e1c533ec download
Q3_K 4 files 28.4 GB
huihui-ai_Qwen3-14B-abliterated-Q3_K_XL.gguf 7.99 GB 891c0965 download
huihui-ai_Qwen3-14B-abliterated-Q3_K_L.gguf 7.36 GB a69fecdb download
huihui-ai_Qwen3-14B-abliterated-Q3_K_M.gguf 6.82 GB 2369b5a7 download
huihui-ai_Qwen3-14B-abliterated-Q3_K_S.gguf 6.20 GB a3ab90db download
IQ4 2 files 15.5 GB
huihui-ai_Qwen3-14B-abliterated-IQ4_NL.gguf 7.95 GB 62fc582f download
huihui-ai_Qwen3-14B-abliterated-IQ4_XS.gguf 7.55 GB fde485b8 download
IQ3 3 files 17.9 GB
huihui-ai_Qwen3-14B-abliterated-IQ3_M.gguf 6.41 GB dd9dfa9e download
huihui-ai_Qwen3-14B-abliterated-IQ3_XS.gguf 5.94 GB c72d3c1a download
huihui-ai_Qwen3-14B-abliterated-IQ3_XXS.gguf 5.53 GB c0c57097 download
Q2_K 2 files 11.4 GB
huihui-ai_Qwen3-14B-abliterated-Q2_K_L.gguf 6.07 GB c1d16d5d download
huihui-ai_Qwen3-14B-abliterated-Q2_K.gguf 5.36 GB c48c51a8 download
IQ2 3 files 13.9 GB
huihui-ai_Qwen3-14B-abliterated-IQ2_M.gguf 4.96 GB fb862087 download
huihui-ai_Qwen3-14B-abliterated-IQ2_S.gguf 4.62 GB 407f4ea4 download
huihui-ai_Qwen3-14B-abliterated-IQ2_XS.gguf 4.37 GB 41e95613 download
Auxiliary files 3 files 7.37 MB
huihui-ai_Qwen3-14B-abliterated.imatrix 7.35 MB c808c317 download
README.md 15.9 KB cd16334d download
.gitattributes 3.58 KB 0103f907 download

README current version from Hugging Face


quantized_by: bartowski
pipeline_tag: text-generation
extra_gated_prompt: 'Usage Warnings

“Risk of Sensitive or Controversial Outputs“: This model’s safety filtering
has been significantly reduced, potentially generating sensitive, controversial,
or inappropriate content. Users should exercise caution and rigorously review generated
outputs.

“Not Suitable for All Audiences:“ Due to limited content filtering, the model’s
outputs may be inappropriate for public settings, underage users, or applications
requiring high security.

“Legal and Ethical Responsibilities“: Users must ensure their usage complies
with local laws and ethical standards. Generated content may carry legal or ethical
risks, and users are solely responsible for any consequences.

“Research and Experimental Use“: It is recommended to use this model for research,
testing, or controlled environments, avoiding direct use in production or public-facing
commercial applications.

“Monitoring and Review Recommendations“: Users are strongly advised to monitor
model outputs in real-time and conduct manual reviews when necessary to prevent
the dissemination of inappropriate content.

“No Default Safety Guarantees“: Unlike standard models, this model has not undergone
rigorous safety optimization. huihui.ai bears no responsibility for any consequences
arising from its use.'
base_model: huihui-ai/Qwen3-14B-abliterated
license: apache-2.0
tags:


Llamacpp imatrix Quantizations of Qwen3-14B-abliterated by huihui-ai

Using llama.cpp release b5284 for quantization.

Original model: https://huggingface.co/huihui-ai/Qwen3-14B-abliterated

All quants made using imatrix option with dataset from here

Run them in LM Studio

Run them directly with llama.cpp, or any other llama.cpp based project

Prompt format

No chat template specified so default is used. This may be incorrect, check original model card for details.

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Download a file (not the whole branch) from below:

Filename Quant type File Size Split Description
Qwen3-14B-abliterated-bf16.gguf bf16 29.54GB false Full BF16 weights.
Qwen3-14B-abliterated-Q8_0.gguf Q8_0 15.70GB false Extremely high quality, generally unneeded but max available quant.
Qwen3-14B-abliterated-Q6_K_L.gguf Q6_K_L 12.50GB false Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended.
Qwen3-14B-abliterated-Q6_K.gguf Q6_K 12.12GB false Very high quality, near perfect, recommended.
Qwen3-14B-abliterated-Q5_K_L.gguf Q5_K_L 10.99GB false Uses Q8_0 for embed and output weights. High quality, recommended.
Qwen3-14B-abliterated-Q5_K_M.gguf Q5_K_M 10.51GB false High quality, recommended.
Qwen3-14B-abliterated-Q5_K_S.gguf Q5_K_S 10.26GB false High quality, recommended.
Qwen3-14B-abliterated-Q4_K_L.gguf Q4_K_L 9.58GB false Uses Q8_0 for embed and output weights. Good quality, recommended.
Qwen3-14B-abliterated-Q4_1.gguf Q4_1 9.39GB false Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
Qwen3-14B-abliterated-Q4_K_M.gguf Q4_K_M 9.00GB false Good quality, default size for most use cases, recommended.
Qwen3-14B-abliterated-Q3_K_XL.gguf Q3_K_XL 8.58GB false Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
Qwen3-14B-abliterated-Q4_K_S.gguf Q4_K_S 8.57GB false Slightly lower quality with more space savings, recommended.
Qwen3-14B-abliterated-Q4_0.gguf Q4_0 8.54GB false Legacy format, offers online repacking for ARM and AVX CPU inference.
Qwen3-14B-abliterated-IQ4_NL.gguf IQ4_NL 8.54GB false Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference.
Qwen3-14B-abliterated-IQ4_XS.gguf IQ4_XS 8.11GB false Decent quality, smaller than Q4_K_S with similar performance, recommended.
Qwen3-14B-abliterated-Q3_K_L.gguf Q3_K_L 7.90GB false Lower quality but usable, good for low RAM availability.
Qwen3-14B-abliterated-Q3_K_M.gguf Q3_K_M 7.32GB false Low quality.
Qwen3-14B-abliterated-IQ3_M.gguf IQ3_M 6.88GB false Medium-low quality, new method with decent performance comparable to Q3_K_M.
Qwen3-14B-abliterated-Q3_K_S.gguf Q3_K_S 6.66GB false Low quality, not recommended.
Qwen3-14B-abliterated-Q2_K_L.gguf Q2_K_L 6.51GB false Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
Qwen3-14B-abliterated-IQ3_XS.gguf IQ3_XS 6.38GB false Lower quality, new method with decent performance, slightly better than Q3_K_S.
Qwen3-14B-abliterated-IQ3_XXS.gguf IQ3_XXS 5.94GB false Lower quality, new method with decent performance, comparable to Q3 quants.
Qwen3-14B-abliterated-Q2_K.gguf Q2_K 5.75GB false Very low quality but surprisingly usable.
Qwen3-14B-abliterated-IQ2_M.gguf IQ2_M 5.32GB false Relatively low quality, uses SOTA techniques to be surprisingly usable.
Qwen3-14B-abliterated-IQ2_S.gguf IQ2_S 4.96GB false Low quality, uses SOTA techniques to be usable.
Qwen3-14B-abliterated-IQ2_XS.gguf IQ2_XS 4.69GB false Low quality, uses SOTA techniques to be usable.

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Downloading using huggingface-cli

Click to view download instructions

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/huihui-ai_Qwen3-14B-abliterated-GGUF --include "huihui-ai_Qwen3-14B-abliterated-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/huihui-ai_Qwen3-14B-abliterated-GGUF --include "huihui-ai_Qwen3-14B-abliterated-Q8_0/*" --local-dir ./

You can either specify a new local-dir (huihui-ai_Qwen3-14B-abliterated-Q8_0) or download them all in place (./)

ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

Click to view Q4_0_X_X information (deprecated

I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.

Click to view benchmarks on an AVX2 system (EPYC7702)
model size params backend threads test t/s % (vs Q4_0)
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 pp512 204.03 ± 1.03 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 pp1024 282.92 ± 0.19 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 pp2048 259.49 ± 0.44 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 tg128 39.12 ± 0.27 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 tg256 39.31 ± 0.69 100%
qwen2 3B Q4_0 1.70 GiB 3.09 B CPU 64 tg512 40.52 ± 0.03 100%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 pp512 301.02 ± 1.74 147%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 pp1024 287.23 ± 0.20 101%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 pp2048 262.77 ± 1.81 101%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 tg128 18.80 ± 0.99 48%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 tg256 24.46 ± 3.04 83%
qwen2 3B Q4_K_M 1.79 GiB 3.09 B CPU 64 tg512 36.32 ± 3.59 90%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 pp512 271.71 ± 3.53 133%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 pp1024 279.86 ± 45.63 100%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 pp2048 320.77 ± 5.00 124%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 tg128 43.51 ± 0.05 111%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 tg256 43.35 ± 0.09 110%
qwen2 3B Q4_0_8_8 1.69 GiB 3.09 B CPU 64 tg512 42.60 ± 0.31 105%

Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation

Which file should I choose?

Click here for details

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Thank you to LM Studio for sponsoring my work.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

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.