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

DexopT/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN

DexopT Llama 8B 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%2FL3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN"
Response includes
  • classification m3
  • files 10
  • hub_downloads_all_time 124
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=DexopT
All 4 models by DexopT
 GET/models?family=llama&method=m3
Sibling llama 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
124
37 last 30d - stable
Likes
0
Model age
8mo ago
created 2026-01-16
Downloads over time
Now135→from25↑440%
206210414625 on Mar 18135 on Oct 11135 on Oct 10MarAprMayJunJulAugSepOct
Mar 18 → Oct 11 · 69 snapshots · spans 207 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/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN this lineage
DexopT/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN↓ 37

Metadata

License
other
Languages
en
Quantizations
BF16
Tags
mnn on-device android ios quantization int4 text-generation llama-3.1 en base_model:DexopT/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN base_model:finetune:DexopT/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN license:other

Related

Other by DexopT
Llama3.2-3b-cybersecurity-abliterated 697 Qwen2.5-Coder-3B-Instruct-abliterated-MNN 105 gemma-3-1b-it-heretic-extreme-uncensored-abliterated-MNN 53
Total size
1002 MB
Files
10
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2026-01-16 19:38
Source huggingface.co/DexopT/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN ↗ Base model WhoIsShe/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN ↗

Files by quantization

BF16 1 file 1002 MB
embeddings_bf16.bin 1002 MB 038776f0 download
Auxiliary files 9 files 4.37 GB
llm.mnn.weight 4.37 GB a87a3ae9 download
tokenizer.txt 1.35 MB 7e66c7b4 download
llm.mnn.json 1.07 MB da68833e download
llm.mnn 546 KB fd950f82 download
.gitattributes 1.58 KB e547efe9 download
README.md 1.24 KB cd3c460d download
export_args.json 1.06 KB bfdb52e2 download
llm_config.json 623 B 5947d244 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
  • llama-3.1
    pipeline_tag: text-generation
    library_name: mnn
    base_model: WhoIsShe/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-MNN

DavidAU/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated (MNN Quantized)

Original model :

This is a 4-bit quantized version of the L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated 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/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.
  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: LLAMA-3.1-8B (Uncensored)

README history 2 versions

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

  1. 2026-01-16Update README.mdd87766d1.2 KB
    Loading...
  2. 2026-01-16Add MNN 4-bit quantized model with Model Card3c5eb411.2 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