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

Enerccio/gemma-4-31b-abliterated

Enerccio Gemma 31B
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/Enerccio%2Fgemma-4-31b-abliterated"
Response includes
  • classification m1
  • files 10
  • benchmarks 11 entries
  • hub_downloads_all_time 67
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=Enerccio
All 2 models by Enerccio
 GET/models?family=gemma&method=m1
Sibling gemma models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
67
6 last 30d - cooling
Likes
0
Model age
5mo ago
created 2026-04-23
Downloads over time
Now71→from15↑373%
1234557715 on Apr 2271 on Oct 1171 on Oct 6AprMayJunJulAugSepOct
Apr 22 → Oct 11 · 64 snapshots · spans 172 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 1.9 UGI
Hazardous 0 UGI
Natural Intelligence 34.36 UGI
Political lean -19.4% UGI
Sensitive-Info 19.81 UGI
SocPol 3.7 UGI
UGI 21.54 UGI
Willingness (10) 2.5 UGI
W10-Adherence 3 UGI
W10-Direct 2 UGI
Writing 38.57 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.

google/gemma-4-31B-it this lineage
Enerccio/gemma-4-31b-abliterated↓ 6

Variants by this author 2 formats · 116 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
Tags
safetensors gemma4 abliterated uncensored en base_model:google/gemma-4-31B-it base_model:finetune:google/gemma-4-31B-it license:apache-2.0 region:us

Related

Other by Enerccio
gemma-4-31b-abliterated-GGUF 110
Same base model
wangzhang/gemma-4-31B-it-abliterated 301K paperscarecrow/Gemma-4-31B-it-abliterated 143K HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP 96K OS-Software/gemma-4-31B-it-qat-q4_0-uncensored-heretic-GGUF 6K LiconStudio/Gemma-4-31B-it-abliterated-GGUF 6K
Total size
58.3 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-23 21:14
Source huggingface.co/Enerccio/gemma-4-31b-abliterated ↗ Base model google/gemma-4-31B-it ↗

Files by quantization

Auxiliary files 10 files 58.3 GB
model-00001-of-00002.safetensors 46.5 GB 698fc8ad download
model-00002-of-00002.safetensors 11.8 GB 080e6a6c download
tokenizer.json 30.7 MB a2619fe1 download
model.safetensors.index.json 116 KB c10382ce download
chat_template.jinja 11.8 KB 33c51c2d download
config.json 4.55 KB 47487a38 download
tokenizer_config.json 2.62 KB f07b8ede download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.22 KB f50317e8 download
generation_config.json 208 B eb915975 download

README current version from Hugging Face

license: apache-2.0
base_model: google/gemma-4-31B-it
tags:

  • abliterated
  • uncensored
    language:
  • en

Gemma-4-31b-abliterated v1.1

Abliterated (uncensored) version of google/gemma-4-31B-it.

Method

Uncensored using Heretic.

  • Trials: 929
  • Refusals: 26/100
  • KL divergence: 0.3687

Numbers from Heretic repo for comparison:

Model Refusals for "harmful" prompts KL divergence from original model for "harmless" prompts
google/gemma-3-12b-it (original) 97/100 0 (by definition)
mlabonne/gemma-3-12b-it-abliterated-v2 3/100 1.04
huihui-ai/gemma-3-12b-it-abliterated 3/100 0.45
p-e-w/gemma-3-12b-it-heretic 3/100 0.16

Notes

Previous version had some artifacts, this one has a fair bit lower divergence and has been more stable.
26% refusals in trial but in practice it works well

License: Apache 2.0 (inherited from the original model).

README history 1 version

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

  1. 2026-04-23Duplicate from Kooten/gemma-4-31b-abliterated-v1.17d189321.2 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