Get the app
← back to catalog · registered 2026-08-29 15:03

llmfan46/Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF

llmfan46 Qwen 122B 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/llmfan46%2FQwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF"
Response includes
  • classification m3
  • files 1
  • hub_downloads_all_time 8,050
  • author_summary 212 models
  • readme_text full
Try next
GET/models?author=llmfan46
All 212 models by llmfan46
 GET/models?family=qwen&method=m3
Sibling qwen 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
8K
HF trending score
1
mild recent interest
Likes
7
Model age
8w ago
created 2026-08-29
Downloads over time
Now12.4K→from0↑0%
04.5K9.1K13.6K0 on Aug 2912.4K on Oct 27AugSepOct
Aug 29 → Oct 27 · 60 snapshots · spans 59 days

Metadata

Tags
transformers gguf qwen3_5_moe heretic uncensored decensored abliterated mtp image-text-to-text base_model:Qwen/Qwen3.5-122B-A10B base_model:finetune:Qwen/Qwen3.5-122B-A10B license:apache-2.0

Related

Other by llmfan46
gemma-4-E4B-it-ultra-uncensored-heretic-GGUF 91K gemma-4-31B-it-uncensored-heretic-GGUF 82K gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUF 64K Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-GGUF 64K gemma-4-26B-A4B-it-uncensored-heretic-GGUF 33K
Total size
0 B
Files
1
Quantizations
1
Registered
2026-08-29 15:03
Last updated on HF
2026-08-30 09:54
Source huggingface.co/llmfan46/Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF ↗

Files by quantization

Auxiliary files 1 file 1.48 KB
.gitattributes 1.48 KB a6344aac download

README

The author did not publish a README.

README history 5 versions

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

  1. 2026-08-29Update README.mdd6e2f4694.6 KB
    Loading...
  2. 2026-08-29Update README.mdf31bde394.6 KB
    Loading...
  3. 2026-08-29Update README.mdf87862d94.6 KB
    Loading...
  4. 2026-08-29Update README.md169481594.6 KB
    Loading...
  5. 2026-08-29Upload folder using huggingface_hub358e9c794.4 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