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

mradermacher/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-GGUF

mradermacher Llama 8B GGUF second-order 8K 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/mradermacher%2FL3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-GGUF"
Response includes
  • classification m3
  • files 14
  • hub_downloads_all_time 5,622
  • author_summary 3324 models
  • readme_text full
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
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · lifetime
6K
1K last 30d - stable
Likes
1
Model age
9mo ago
created 2025-12-18
Downloads over time
Now5.9K→from526↑1,012%
2602.3K4.3K6.4K526 on Dec 17, 20255.9K on Oct 11Dec '25FebAprJunAugOct
Dec 17, 2025 → Oct 11 · 82 snapshots · spans 298 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.

Variants by this author 2 formats · 3K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Languages
en
Quantizations
F16 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf heretic uncensored decensored abliterated finetune creative creative writing fiction writing plot generation sub-plot generation

Related

Total size
66.9 GB
Files
14
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2025-12-18 11:54

Files by quantization

F16 1 file 15.0 GB
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.f16.gguf 15.0 GB a6b7a43f download
Q8_0 1 file 7.95 GB
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q8_0.gguf 7.95 GB 7642a979 download
Q6_K 1 file 6.14 GB
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q6_K.gguf 6.14 GB 696406fb download
Q5_K 2 files 10.6 GB
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q5_K_M.gguf 5.34 GB 49f57a66 download
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q5_K_S.gguf 5.21 GB 783dfa14 download
Q4_K 2 files 8.95 GB
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q4_K_M.gguf 4.58 GB 9855c39b download
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q4_K_S.gguf 4.37 GB 3b178175 download
IQ4 1 file 4.18 GB
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.IQ4_XS.gguf 4.18 GB 2b456aa1 download
Q3_K 3 files 11.2 GB
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q3_K_L.gguf 4.03 GB 0d437d1b download
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q3_K_M.gguf 3.74 GB 9b341f65 download
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q3_K_S.gguf 3.41 GB c14a9146 download
Q2_K 1 file 2.96 GB
L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated.Q2_K.gguf 2.96 GB e971a3bd download
Auxiliary files 2 files 7.35 KB
README.md 4.74 KB e8f58bc1 download
.gitattributes 2.61 KB 0d243360 download

README current version from Hugging Face


base_model: DavidAU/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated
language:

  • en
    library_name: transformers
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • heretic
  • uncensored
  • decensored
  • abliterated
  • finetune
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • fiction writing
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prose
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • swearing
  • rp
  • llama3
  • llama-3
  • enhanced quants
  • max quants
  • maxcpu quants
  • horror

About

static quants of https://huggingface.co/DavidAU/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated

For a convenient overview and download list, visit our model page for this model.

weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs
for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF Q2_K 3.3
GGUF Q3_K_S 3.8
GGUF Q3_K_M 4.1 lower quality
GGUF Q3_K_L 4.4
GGUF IQ4_XS 4.6
GGUF Q4_K_S 4.8 fast, recommended
GGUF Q4_K_M 5.0 fast, recommended
GGUF Q5_K_S 5.7
GGUF Q5_K_M 5.8
GGUF Q6_K 6.7 very good quality
GGUF Q8_0 8.6 fast, best quality
GGUF f16 16.2 16 bpw, overkill

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

README history 4 versions

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

  1. 2025-12-18auto-patch README.md26342134.7 KB
    Loading...
  2. 2025-12-18auto-patch README.md9bb664c4.8 KB
    Loading...
  3. 2025-12-18auto-patch README.mdee9ab134.6 KB
    Loading...
  4. 2025-12-18uploaded from marcobf79c13399 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.

Open in Abliteration