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

Yingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic

Yingyaeliae 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/Yingyaeliae%2FL3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic"
Response includes
  • classification m3
  • files 6
  • hub_downloads_all_time 1,240
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=Yingyaeliae
All 2 models by Yingyaeliae
 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
1K
373 last 30d - stable
Likes
1
Model age
3mo ago
created 2026-06-25
Downloads over time
Now1.4K→from245↑480%
1866371.1K1.5K245 on Jun 241.4K on Oct 12JunJulAugSepOct
Jun 24 → Oct 12 · 56 snapshots · spans 110 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.

NousResearch/Hermes-3-Llama-3.1-8B this lineage
Yingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic↓ 373

Metadata

License
other
Quantizations
Q4_K Q5_K Q6_K Q8_0
Tags
gguf text-generation-inference llama-cpp heretic text-generation base_model:NousResearch/Hermes-3-Llama-3.1-8B base_model:quantized:NousResearch/Hermes-3-Llama-3.1-8B license:other endpoints_compatible region:us conversational

Related

Other by Yingyaeliae
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic 24
Same base model
gulan28/Hermes-3-Llama-3.1-8B-GGUF-abliterated 24
Total size
24.0 GB
Files
6
Quantizations
5
Registered
2026-08-22 13:56
Last updated on HF
2026-06-25 08:46
Source huggingface.co/Yingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic ↗ Base model NousResearch/Hermes-3-Llama-3.1-8B ↗

Files by quantization

Q8_0 1 file 7.95 GB
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q8_0.gguf 7.95 GB 930fd320 download
Q6_K 1 file 6.14 GB
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q6_K.gguf 6.14 GB 6bd3409e download
Q5_K 1 file 5.34 GB
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q5_K_M.gguf 5.34 GB e1cdadff download
Q4_K 1 file 4.58 GB
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q4_K_M.gguf 4.58 GB 65dfe287 download
Auxiliary files 2 files 2.75 KB
.gitattributes 1.92 KB ae59d51c download
README.md 852 B 19511651 download

README current version from Hugging Face

license: other
base_model: NousResearch/Hermes-3-Llama-3.1-8B
tags:

  • text-generation-inference
  • llama-cpp
  • gguf
  • heretic
    pipeline_tag: text-generation
    quantized_by: llama.cpp

L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic

This repository contains GGUF format quantizations of the model using llama.cpp.

3/100 Refusal via Heretic 1.4 by https://github.com/p-e-w/heretic

Available Quants:

  • Q4_K_M: 4-bit medium quantization (balanced performance/size).
  • Q5_K_M: 5-bit medium quantization (recommended sweet spot for 8B).
  • Q6_K: 6-bit quantization (extremely close to unquantized quality).
  • Q8_0: 8-bit standard quantization.

How to use with llama.cpp:

./llama-cli -m L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q5_K_M.gguf -n 512 -ngl 999 -co -i

README history 5 versions

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

  1. 2026-06-25Update README.md48cdac6852 B
    Loading...
  2. 2026-06-25Update README.md70b7280790 B
    Loading...
  3. 2026-06-25Update README.mde92a53d782 B
    Loading...
  4. 2026-06-25Update README.md7ebc441777 B
    Loading...
  5. 2026-06-25Upload README.md with huggingface_hubd919bfd764 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