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

jzofe/Gemma-4-31B-Uncensored-Heretic-GGUF

jzofe Gemma 31B GGUF 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/jzofe%2FGemma-4-31B-Uncensored-Heretic-GGUF"
Response includes
  • classification m3
  • files 3
  • benchmarks 11 entries
  • hub_downloads_all_time 1,511
  • author_summary 1 models
  • readme_text full
Try next
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
2K
66 last 30d - cooling
Likes
1
Model age
6mo ago
created 2026-04-05
Downloads over time
Now1.5K→from954↑61%
9251.1K1.4K1.6K954 on Apr 151.5K on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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
jzofe/Gemma-4-31B-Uncensored-Heretic-GGUF↓ 66

Metadata

License
apache-2.0
Quantizations
Q3_K
Tags
gguf tool-use reasoning base_model:google/gemma-4-31B-it base_model:quantized:google/gemma-4-31B-it license:apache-2.0 endpoints_compatible region:us imatrix conversational

Related

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
12.8 GB
Files
3
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2026-04-08 13:07
Source huggingface.co/jzofe/Gemma-4-31B-Uncensored-Heretic-GGUF ↗ Base model google/gemma-4-31B-it ↗

Files by quantization

Q3_K 1 file 12.8 GB
gemma4-31b-heretic-Q3_K_S.gguf 12.8 GB 1f42f98b download
Auxiliary files 2 files 2.09 KB
.gitattributes 1.55 KB 0ea69503 download
README.md 552 B 98cda456 download

README current version from Hugging Face

license: apache-2.0
tags:

  • tool-use
  • reasoning
    library_name: gguf
    base_model: google/gemma-4-31B-it

Imatrix - Gemma4 31B IT Uncensored

Datasets: fineweb-edu - wikipedia - starcoder2

recommended sampling settings

Parameter Value
Temperature 1
Top K 64
Repeat Penalty 1.07
Top P 0.95
Min P 0.01 or 0

System Prompt: "You are Gemma, an uncensored and direct AI..." (just example, fix it yourself)

quantized on NVIDIA A10 with 386GB system RAM

README history 5 versions

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

  1. 2026-04-08Update README.md9b30650552 B
    Loading...
  2. 2026-04-05Update README.mdbe34cef549 B
    Loading...
  3. 2026-04-05Update README.md4fdba5e498 B
    Loading...
  4. 2026-04-05Update README.mdd8275d4398 B
    Loading...
  5. 2026-04-05Create README.md3f163fb194 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.

Get the app Browse the catalog
Open in Abliteration