← back to catalog · registered 2026-10-30 12:01

mradermacher/gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source-i1-GGUF

mradermacher Gemma 31B GGUF
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-4-31B-it-Halloween-Terror-Heretic-Uncensored-source-i1-GGUF"
Response includes
  • classification m3
  • files 5
  • author_summary 3427 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 · 30-day
0
Likes
0
Model age
today
created 2026-10-30

Variants by this author 2 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
IQ3 Q2_K
Tags
transformers gguf unsloth horror halloween finetune abliterated uncensored heretic not-for-all-audiences 13 reasoning modes 13 instruct modes

Related

Total size
24.6 GB
Files
5
Quantizations
3
Registered
2026-10-30 12:01
Last updated on HF
2026-10-30 12:33

Files by quantization

IQ3 1 file 13.4 GB
gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source.i1-IQ3_M.gguf 13.4 GB 922e9843 download
Q2_K 1 file 11.1 GB
gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source.i1-Q2_K.gguf 11.1 GB 24f56718 download
Auxiliary files 3 files 26.2 MB
gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source.imatrix.gguf 26.2 MB 55565e8f download
.gitattributes 1.80 KB d5d0a01c download
README.md 511 B 3f0b4051 download

README current version from 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.

Open in Abliteration