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

mradermacher/Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic-GGUF

mradermacher Mistral 24B 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%2FMistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic-GGUF"
Response includes
  • classification m3
  • files 15
  • benchmarks 11 entries
  • hub_downloads_all_time 4,940
  • author_summary 3324 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · lifetime
5K
2K last 30d - stable
Likes
3
Model age
6mo ago
created 2026-03-21
Downloads over time
Now5.4K→from0↑0%
02K4K6K0 on Mar 185.4K on Oct 11MarAprMayJunJulAugSepOct
Mar 18 → Oct 11 · 69 snapshots · spans 207 days

Benchmarks

Benchmark Score Source
Entertainment 0.6 UGI
Hazardous 0.6 UGI
Natural Intelligence 5.09 UGI
Political lean NA UGI
Sensitive-Info 4.06 UGI
SocPol 0 UGI
UGI 4.38 UGI
Willingness (10) 0.5 UGI
W10-Adherence 0 UGI
W10-Direct 1 UGI
Writing NA 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.

Variants by this author 2 formats · 4K downloads combined

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

Metadata

License
apache-2.0
Languages
en fr de es pt it ja ko ru zh ar fa id ms ne pl ro sr sv tr uk vi hi bn
Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf heretic uncensored decensored abliterated ara en fr de es pt

Related

Total size
150 GB
Files
15
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-10-11 00:02

Files by quantization

Q8_0 2 files 23.8 GB
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q8_0.gguf 23.3 GB 3138e5ff download
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.mmproj-Q8_0.gguf 458 MB e1a19540 download
Q6_K 1 file 18.0 GB
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q6_K.gguf 18.0 GB 1a87065a download
Q5_K 2 files 30.8 GB
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q5_K_M.gguf 15.6 GB b9e43c45 download
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q5_K_S.gguf 15.2 GB 081b869c download
Q4_K 2 files 26.0 GB
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q4_K_M.gguf 13.3 GB f760b3f2 download
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q4_K_S.gguf 12.6 GB 0dc8508a download
IQ4 1 file 12.0 GB
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.IQ4_XS.gguf 12.0 GB 970d476a download
Q3_K 3 files 31.9 GB
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q3_K_L.gguf 11.5 GB 0d88b8c8 download
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q3_K_M.gguf 10.7 GB 5954f53c download
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q3_K_S.gguf 9.69 GB 02dd8832 download
Q2_K 1 file 8.28 GB
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.Q2_K.gguf 8.28 GB e69321b7 download
F16 1 file 837 MB
Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic.mmproj-f16.gguf 837 MB 19579475 download
Auxiliary files 2 files 7.96 KB
README.md 5.09 KB 4a3fa681 download
.gitattributes 2.87 KB a5cf165b download

README current version from Hugging Face


base_model: llmfan46/Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic
language:

  • en
  • fr
  • de
  • es
  • pt
  • it
  • ja
  • ko
  • ru
  • zh
  • ar
  • fa
  • id
  • ms
  • ne
  • pl
  • ro
  • sr
  • sv
  • tr
  • uk
  • vi
  • hi
  • bn
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • heretic
  • uncensored
  • decensored
  • abliterated
  • ara

About

static quants of https://huggingface.co/llmfan46/Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic-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 mmproj-Q8_0 0.6 multi-modal supplement
GGUF mmproj-f16 1.0 multi-modal supplement
GGUF Q2_K 9.0
GGUF Q3_K_S 10.5
GGUF Q3_K_M 11.6 lower quality
GGUF Q3_K_L 12.5
GGUF IQ4_XS 13.0
GGUF Q4_K_S 13.6 fast, recommended
GGUF Q4_K_M 14.4 fast, recommended
GGUF Q5_K_S 16.4
GGUF Q5_K_M 16.9
GGUF Q6_K 19.4 very good quality
GGUF Q8_0 25.2 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 4 versions

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

  1. 2026-10-11auto-patch README.md353d8dd5.3 KB
    Loading...
  2. 2026-03-21auto-patch README.md8ee86ef5.1 KB
    Loading...
  3. 2026-03-21auto-patch README.md21a321c4.9 KB
    Loading...
  4. 2026-03-21uploaded from nico178a66f6412 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