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

mradermacher/aya-expanse-32b-abliterated-GGUF

mradermacher 32B GGUF second-order 8K 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%2Faya-expanse-32b-abliterated-GGUF"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 8,770
  • 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 layer-wise ablation 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='huihui-ai/aya-expanse-32b-abliterated' (base is huihui-ai model (M3))
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
365 last 30d - cooling
Likes
4
Model age
22mo ago
created 2024-12-15
Downloads over time
Now8.8K→from361↑2,342%
03.2K6.4K9.7K361 on Dec 11, 20248.8K on Oct 118.8K on Oct 9Dec '24Mar '25Jun '25Sep '25Dec '25MarJunSep
Dec 11, 2024 → Oct 11 · 135 snapshots · spans 669 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 · 980 downloads combined

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

Metadata

Languages
en fr de es it pt ja ko zh ar el fa pl id cs he hi nl ro ru tr uk vi
Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf abliterated uncensored en fr de es it pt ja ko

Related

Total size
209 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2024-12-15 05:44

Files by quantization

Q8_0 1 file 32.0 GB
aya-expanse-32b-abliterated.Q8_0.gguf 32.0 GB c5b9580a download
Q6_K 1 file 24.7 GB
aya-expanse-32b-abliterated.Q6_K.gguf 24.7 GB 1d990afe download
Q5_K 2 files 42.4 GB
aya-expanse-32b-abliterated.Q5_K_M.gguf 21.5 GB d6a2f3f8 download
aya-expanse-32b-abliterated.Q5_K_S.gguf 20.9 GB 48d639b8 download
Q4_K 2 files 36.0 GB
aya-expanse-32b-abliterated.Q4_K_M.gguf 18.4 GB 4df0000f download
aya-expanse-32b-abliterated.Q4_K_S.gguf 17.6 GB 831cc4a8 download
IQ4 1 file 16.8 GB
aya-expanse-32b-abliterated.IQ4_XS.gguf 16.8 GB f1020f87 download
Q3_K 3 files 45.2 GB
aya-expanse-32b-abliterated.Q3_K_L.gguf 16.4 GB 88ae78b6 download
aya-expanse-32b-abliterated.Q3_K_M.gguf 15.1 GB 7e6556e7 download
aya-expanse-32b-abliterated.Q3_K_S.gguf 13.7 GB 16703b04 download
Q2_K 1 file 11.9 GB
aya-expanse-32b-abliterated.Q2_K.gguf 11.9 GB 4a131555 download
Auxiliary files 2 files 6.25 KB
README.md 3.96 KB fc38be83 download
.gitattributes 2.29 KB 6705da59 download

README current version from Hugging Face


base_model: huihui-ai/aya-expanse-32b-abliterated
extra_gated_fields:
Affiliation: text
Country: country
I agree to use this model for non-commercial use ONLY: checkbox
Name: text
extra_gated_prompt: By submitting this form, you agree to the License Agreement and
acknowledge that the information you provide will be collected, used, and shared
in accordance with Cohere’s Privacy Policy. You’ll
receive email updates about C4AI and Cohere research, events, products and services.
You can unsubscribe at any time.
language:

  • en
  • fr
  • de
  • es
  • it
  • pt
  • ja
  • ko
  • zh
  • ar
  • el
  • fa
  • pl
  • id
  • cs
  • he
  • hi
  • nl
  • ro
  • ru
  • tr
  • uk
  • vi
    library_name: transformers
    license: cc-by-nc-4.0
    quantized_by: mradermacher
    tags:
  • abliterated
  • uncensored

About

static quants of https://huggingface.co/huihui-ai/aya-expanse-32b-abliterated

weighted/imatrix quants are available at https://huggingface.co/mradermacher/aya-expanse-32b-abliterated-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 12.9
GGUF Q3_K_S 14.8
GGUF Q3_K_M 16.3 lower quality
GGUF Q3_K_L 17.7
GGUF IQ4_XS 18.1
GGUF Q4_K_S 18.9 fast, recommended
GGUF Q4_K_M 19.9 fast, recommended
GGUF Q5_K_S 22.6
GGUF Q5_K_M 23.2
GGUF Q6_K 26.6 very good quality
GGUF Q8_0 34.4 fast, best quality

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 2 versions

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

  1. 2024-12-15auto-patch README.md59793b94 KB
    Loading...
  2. 2024-12-15uploaded from kaos291498a227 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