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

mradermacher/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUF

mradermacher Gemma 31B GGUF second-order 262K 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%2Fgemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUF"
Response includes
  • classification m3
  • files 15
  • hub_downloads_all_time 6,097
  • 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
6K
2K last 30d - stable
Likes
5
Model age
4mo ago
created 2026-05-18
Downloads over time
Now6.9K→from1.9K↑254%
1.3K3.4K5.4K7.4K1.9K on May 206.9K on Oct 12MayJunJulAugSepOct
May 20 → Oct 12 · 62 snapshots · spans 145 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 · 5K 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 jpn
Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf text-generation-inference unsloth gemma4 heretic uncensored decensored abliterated ara creative writing translation

Related

Total size
197 GB
Files
15
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-10-08 23:19

Files by quantization

Q8_0 2 files 31.1 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q8_0.gguf 30.4 GB 679a2684 download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.mmproj-Q8_0.gguf 772 MB 0a6c0277 download
Q6_K 1 file 23.5 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q6_K.gguf 23.5 GB 66d0e850 download
Q5_K 2 files 40.2 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q5_K_M.gguf 20.3 GB 9b28a6c9 download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q5_K_S.gguf 19.8 GB ba92bdaa download
Q4_K 2 files 33.9 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q4_K_M.gguf 17.4 GB 763966aa download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q4_K_S.gguf 16.5 GB 5d097ffd download
IQ4 1 file 15.7 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.IQ4_XS.gguf 15.7 GB 9486c4e3 download
Q3_K 3 files 42.5 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q3_K_L.gguf 15.5 GB a12001d4 download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q3_K_M.gguf 14.2 GB ed270ef5 download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q3_K_S.gguf 12.8 GB f44cfb6b download
Q2_K 1 file 11.1 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.Q2_K.gguf 11.1 GB c7c05803 download
F16 1 file 1.12 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic.mmproj-f16.gguf 1.12 GB 2e4c62fb download
Auxiliary files 2 files 8.26 KB
README.md 5.32 KB 8059c9be download
.gitattributes 2.93 KB 33a4f712 download

README current version from Hugging Face


base_model: llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic
language:

  • en
  • jpn
    library_name: transformers
    license: apache-2.0
    license_link: https://ai.google.dev/gemma/docs/gemma_4_license
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • text-generation-inference
  • transformers
  • unsloth
  • gemma4
  • heretic
  • uncensored
  • decensored
  • abliterated
  • ara
  • creative writing
  • translation
  • visual novels
  • finetune
  • roleplay
  • rp

About

static quants of https://huggingface.co/llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-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/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-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 0.9 multi-modal supplement
GGUF mmproj-f16 1.3 multi-modal supplement
GGUF Q2_K 12.0
GGUF Q3_K_S 13.9
GGUF Q3_K_M 15.4 lower quality
GGUF Q3_K_L 16.7
GGUF IQ4_XS 17.0
GGUF Q4_K_S 17.9 fast, recommended
GGUF Q4_K_M 18.8 fast, recommended
GGUF Q5_K_S 21.4
GGUF Q5_K_M 21.9
GGUF Q6_K 25.3 very good quality
GGUF Q8_0 32.7 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 5 versions

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

  1. 2026-10-08auto-patch README.mdfaf28a65.5 KB
    Loading...
  2. 2026-05-18auto-patch README.mdb30bbe25.3 KB
    Loading...
  3. 2026-05-18auto-patch README.md49b4f485.4 KB
    Loading...
  4. 2026-05-18auto-patch README.md082d8235.2 KB
    Loading...
  5. 2026-05-18uploaded from nico11e056c0417 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