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

DexopT/gemma-3-1b-it-heretic-extreme-uncensored-abliterated-MNN

DexopT Gemma 1B second-order
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/DexopT%2Fgemma-3-1b-it-heretic-extreme-uncensored-abliterated-MNN"
Response includes
  • classification m3
  • files 9
  • hub_downloads_all_time 169
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=DexopT
All 4 models by DexopT
 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
169
53 last 30d - stable
Likes
1
Model age
8mo ago
created 2026-01-16
Downloads over time
Now194→from43↑351%
359315120943 on Mar 18194 on Oct 12MarAprMayJunJulAugSepOct
Mar 18 → Oct 12 · 70 snapshots · spans 208 days

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.

WhoIsShe/gemma-3-1b-it-heretic-extreme-uncensored-abliterated this lineage
DexopT/gemma-3-1b-it-heretic-extreme-uncensored-abliterated-MNN↓ 53

Metadata

License
other
Languages
en
Tags
mnn on-device android ios quantization int4 text-generation gemma en base_model:DexopT/gemma-3-1b-it-heretic-extreme-uncensored-abliterated-MNN base_model:finetune:DexopT/gemma-3-1b-it-heretic-extreme-uncensored-abliterated-MNN license:other

Related

Other by DexopT
Llama3.2-3b-cybersecurity-abliterated 697 Qwen2.5-Coder-3B-Instruct-abliterated-MNN 105 L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN 37
Total size
0 B
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-01-16 19:06
Source huggingface.co/DexopT/gemma-3-1b-it-heretic-extreme-uncensored-abliterated-MNN ↗ Base model WhoIsShe/gemma-3-1b-it-heretic-extreme-uncensored-abliterated ↗

Files by quantization

Auxiliary files 9 files 605 MB
llm.mnn.weight 597 MB 813c1d60 download
tokenizer.txt 6.05 MB c528aed4 download
llm.mnn.json 1.02 MB b9ea4b44 download
llm.mnn 525 KB fb5c2bda download
llm_config.json 1.90 KB 90a928d6 download
.gitattributes 1.58 KB e547efe9 download
export_args.json 1.07 KB 5f4dc380 download
README.md 1.00 KB feef3da8 download
config.json 210 B bd685f44 download

README current version from Hugging Face

language:

  • en
    license: other
    tags:
  • mnn
  • on-device
  • android
  • ios
  • quantization
  • int4
  • text-generation
  • gemma
    pipeline_tag: text-generation
    library_name: mnn
    base_model: WhoIsShe/gemma-3-1b-it-heretic-extreme-uncensored-abliterated

Gemma-3-1B (MNN Quantized)

This is a 4-bit quantized version of the Gemma-3-1B model, optimized for on-device inference (Android/iOS) using the Alibaba MNN framework.

🚀 Fast Deployment on Android

1. Download the App

Don't build from scratch! Use the official MNN Chat Android app:

2. Setup

  1. Download the files from this repo (llm.mnn, llm.mnn.weight, config.json).
  2. Create a folder on your phone: /sdcard/MNN/gemma-3-1b.
  3. Copy the files into that folder.
  4. Open the MNN App and select your folder.

💻 Technical Details

  • Framework: MNN
  • Quantization: 4-bit Asymmetric (Int4)
  • Model Type: Gemma-3-1B (Uncensored)

README history 1 version

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

  1. 2026-01-16Add MNN 4-bit quantized model with Model Carde5c4fa41 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