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

DavidAU/gemma-4-E2B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking

DavidAU Gemma 5.1B
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/DavidAU%2Fgemma-4-E2B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking"
Response includes
  • classification m3
  • files 9
  • benchmarks 11 entries
  • hub_downloads_all_time 2,807
  • author_summary 213 models
  • readme_text full
Try next
GET/models?author=DavidAU
All 213 models by DavidAU
 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
3K
125 last 30d - cooling
Likes
7
Descendants
2
in 2 direct forks
Model age
4mo ago
created 2026-05-16
Downloads over time
Now2.9K→from99↑2,828%
01.1K2.1K3.2K99 on May 202.9K on Oct 11MayJunJulAugSepOct
May 20 → Oct 11 · 60 snapshots · spans 144 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 0.9 UGI
Hazardous 0 UGI
Natural Intelligence 13.78 UGI
Political lean -15.8% UGI
Sensitive-Info 3.65 UGI
SocPol 0 UGI
UGI 5.76 UGI
Willingness (10) 1 UGI
W10-Adherence 0 UGI
W10-Direct 2 UGI
Writing 17.3 UGI

Genealogy 2 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.

google/gemma-4-E2B-it this lineage
DavidAU/gemma-4-E2B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking↓ 125 2 forks
mradermacher/gemma-4-E2B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUF↓ 965
mradermacher/gemma-4-E2B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF↓ 899

Metadata

License
apache-2.0
Tags
transformers safetensors gemma4 image-text-to-text heretic uncensored aliterated finetune unsloth all use cases coder creative

Related

Other by DavidAU
Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 2.1M Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 2M Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 476K Qwen3-8B-64k-Context-2X-Josiefied-Uncensored 240K Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 220K
Same base model
TrevorJS/gemma-4-E2B-it-uncensored 12K huihui-ai/Huihui-gemma-4-E2B-it-abliterated 3K prithivMLmods/ultragemma4-e2b-heretic-uncensored 924 Momix-44/Huihui-gemma-4-E2B-it-abliterated-v2 870 DuoNeural/Gemma-4-E2B-Abliterated-GGUF 681
Total size
9.54 GB
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-19 02:19
Source huggingface.co/DavidAU/gemma-4-E2B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking ↗ Base model google/gemma-4-E2B-it ↗

Files by quantization

Auxiliary files 9 files 9.57 GB
model.safetensors 9.54 GB a71b19b3 download
tokenizer.json 30.7 MB cc8d3a0c download
chat_template.jinja 16.0 KB 79ada2d9 download
config.json 4.84 KB 923b5e94 download
tokenizer_config.json 2.02 KB e5418067 download
processor_config.json 1.65 KB 5465974d download
.gitattributes 1.53 KB 52373fe2 download
README.md 986 B 7c454098 download
generation_config.json 208 B e605bb45 download

README current version from Hugging Face

license: apache-2.0
base_model:

  • google/gemma-4-E2B-it
    pipeline_tag: any-to-any
    library_name: transformers
    tags:
  • heretic
  • uncensored
  • aliterated
  • finetune
  • unsloth
  • finetune
  • 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

gemma-4-E2B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking

  • uncensored, then fine tuned.
  • in testing
IN HOUSE BENCHMARKS [by Nightmedia]:

         arc-c arc/e boolq hswag obkqa piqa  wino

gemma-4-E2B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
mxfp8    0.389,0.480,0.767,0.599,0.408,0.729,0.629

---

BASE UNTUNED MODEL:

gemma-4-E2B-it
bf16     0.389,0.465,0.762,0.486,0.372,0.707,0.641
q8-hi    0.392,0.462,0.762,0.487,0.376,0.706,0.636

README history 2 versions

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

  1. 2026-05-19Update README.md5a385da986 B
    Loading...
  2. 2026-05-17Create README.md5dbd90b654 B
    Loading...

Discussions 1 thread

  1. 2026-05-20Thanks!open1 💬#1
    Loading...

Continue on Hugging Face →

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