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

HuyEdits/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-modified

HuyEdits Llama 8B GGUF 131K 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/HuyEdits%2FLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-modified"
Response includes
  • classification m3
  • files 4
  • hub_downloads_all_time 864
  • author_summary 1 models
  • readme_text full
Try next
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
864
53 last 30d - cooling
Likes
0
Model age
7mo ago
created 2026-03-01
Downloads over time
Now895→from564↑59%
547674801928564 on Mar 4895 on Oct 12895 on Oct 11MarAprMayJunJulAugSepOct
Mar 4 → Oct 12 · 72 snapshots · spans 222 days

Metadata

Tags
safetensors gguf en dataset:nohurry/Opus-4.6-Reasoning-3000x-filtered base_model:DavidAU/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning base_model:quantized:DavidAU/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning license:apache-2.0 endpoints_compatible region:us conversational
Total size
9.17 GB
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-01 11:44
Source huggingface.co/HuyEdits/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-modified ↗

Files by quantization

Auxiliary files 4 files 9.17 GB
model-v3-q4.gguf 4.58 GB adf0095b download
model-q4.gguf 4.58 GB a14654bd download
.gitattributes 1.86 KB 5bdd447d download
README.md 203 B eeeca8d9 download

README current version from Hugging Face

license: apache-2.0
datasets:

  • nohurry/Opus-4.6-Reasoning-3000x-filtered
    language:
  • en
    base_model:

    DavidAU/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning

README history 1 version

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

  1. 2026-03-01Create README.mdc67a360203 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