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

Jackxuanxuan/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF

Jackxuanxuan 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/Jackxuanxuan%2Fgemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF"
Response includes
  • classification m3
  • files 10
  • benchmarks 11 entries
  • hub_downloads_all_time 1,090
  • author_summary 10 models
  • readme_text full
Try next
GET/models?author=Jackxuanxuan
All 10 models by Jackxuanxuan
 GET/models?family=gemma&method=m3
Sibling gemma models · same method
 GET/methods/m3
What "m3" means · taxonomy
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
M1 Direct removal →
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)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
1K
161 last 30d - stable
Likes
0
Model age
3mo ago
created 2026-06-15
Downloads over time
Now1.1K→from347↑227%
3086109121.2K347 on Jun 171.1K on Oct 11JunJulAugSepOct
Jun 17 → Oct 11 · 56 snapshots · spans 116 days

Benchmarks

Benchmark Score Source
Entertainment 2.8 UGI
Hazardous 4.7 UGI
Natural Intelligence 34.42 UGI
Political lean -22.2% UGI
Sensitive-Info 32.29 UGI
SocPol 2.6 UGI
UGI 52.36 UGI
Willingness (10) 9.2 UGI
W10-Adherence 8.5 UGI
W10-Direct 10 UGI
Writing 38.68 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.

DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking↓ 540 this lineage
Jackxuanxuan/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF↓ 161

Variants by this author 2 formats · 201 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
Quantizations
Q4 Q4_K Q5_K Q6_K
Tags
transformers gguf heretic abliterated uncensored finetune unsloth all use cases coder creative creative writing fiction writing

Related

Other by Jackxuanxuan
gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-i1-GGUF 1K gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-GGUF 468 gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-Instruct-GGUF 214 Gemma-4-Garnet-V2-31B-it-ultra-uncensored-heretic-GGUF 102 Gemma-4-Garnet-V2-31B-it-ultra-uncensored-heretic-i1-GGUF 90
Same base model
mradermacher/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF 46K AEON-7/Gemma-4-31B-it-DECKARD-HERETIC-Uncensored-NVFP4 7K AEON-7/Gemma-4-31B-it-DECKARD-HERETIC-Uncensored-NVFP4-SVDQuant 7K mradermacher/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUF 4K connstruct/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking 545
Total size
132 GB
Files
10
Quantizations
5
Registered
2026-08-22 13:56
Last updated on HF
2026-06-15 14:55
Source huggingface.co/Jackxuanxuan/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF ↗ Base model DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking →

Files by quantization

Q6_K 1 file 23.5 GB
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking.i1-Q6_K.gguf 23.5 GB 25c71f5d download
Q5_K 2 files 40.2 GB
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking.i1-Q5_K_M.gguf 20.3 GB e64cd927 download
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking.i1-Q5_K_S.gguf 19.8 GB 06120be1 download
Q4 2 files 34.6 GB
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking.i1-Q4_1.gguf 18.1 GB 2dd36864 download
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking.i1-Q4_0.gguf 16.5 GB 68bced36 download
Q4_K 2 files 33.9 GB
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking.i1-Q4_K_M.gguf 17.4 GB 6435f225 download
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking.i1-Q4_K_S.gguf 16.5 GB 6d393f84 download
Auxiliary files 3 files 13.1 MB
gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking.imatrix.gguf 13.1 MB 48822c00 download
README.md 8.18 KB 1a14aaf9 download
.gitattributes 3.95 KB e884bb85 download

README current version from Hugging Face

base_model: DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
language:

  • en
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • heretic
  • abliterated
  • uncensored
  • finetune
  • unsloth
  • all use cases
  • coder
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • fiction writing
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prosing
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • all use cases

About

weighted/imatrix quants of https://huggingface.co/DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking

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

static quants are available at https://huggingface.co/mradermacher/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

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 imatrix 0.1 imatrix file (for creating your own quants)
GGUF i1-IQ1_S 7.3 for the desperate
GGUF i1-IQ1_M 7.8 mostly desperate
GGUF i1-IQ2_XXS 8.8
GGUF i1-IQ2_XS 9.6
GGUF i1-IQ2_S 10.3
GGUF i1-IQ2_M 11.0
GGUF i1-Q2_K_S 11.1 very low quality
GGUF i1-Q2_K 12.0 IQ3_XXS probably better
GGUF i1-IQ3_XXS 12.2 lower quality
GGUF i1-IQ3_XS 13.2
GGUF i1-IQ3_S 13.9 beats Q3_K*
GGUF i1-Q3_K_S 13.9 IQ3_XS probably better
GGUF i1-IQ3_M 14.5
GGUF i1-Q3_K_M 15.4 IQ3_S probably better
GGUF i1-Q3_K_L 16.7 IQ3_M probably better
GGUF i1-IQ4_XS 16.8
GGUF i1-Q4_0 17.8 fast, low quality
GGUF i1-Q4_K_S 17.9 optimal size/speed/quality
GGUF i1-Q4_K_M 18.8 fast, recommended
GGUF i1-Q4_1 19.6
GGUF i1-Q5_K_S 21.4
GGUF i1-Q5_K_M 21.9
GGUF i1-Q6_K 25.3 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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

README history 1 version

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

  1. 2026-06-15Duplicate from mradermacher/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thi...db302fa8.2 KB
    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.

Get the app Browse the catalog
Open in Abliteration