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

LoveGlaze/L3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated-Q4_K_M-GGUF

LoveGlaze Llama 16B 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/LoveGlaze%2FL3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated-Q4_K_M-GGUF"
Response includes
  • classification m3
  • files 3
  • hub_downloads_all_time 587
  • author_summary 1 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
587
37 last 30d - cooling
Likes
0
Model age
9mo ago
created 2026-01-01
Downloads over time
Now596→from41↑1,354%
1322643965241 on Dec 31, 2025596 on Oct 11596 on Oct 10Dec '25FebAprJunAugOct
Dec 31, 2025 → Oct 11 · 80 snapshots · spans 284 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.

Metadata

Tags
transformers gguf heretic uncensored decensored abliterated finetune creative creative writing fiction writing plot generation sub-plot generation

Related

Total size
8.97 GB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-01-01 04:32

Files by quantization

Auxiliary files 3 files 8.97 GB
l3-darkest-planet-16b-heretic-uncensored-abliterated-q4_k_m.gguf 8.97 GB 8c66d4c1 download
README.md 2.61 KB c7ed7a9c download
.gitattributes 1.58 KB a76043c3 download

README current version from Hugging Face


library_name: transformers
base_model: DavidAU/L3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated
tags:

  • heretic
  • uncensored
  • decensored
  • abliterated
  • finetune
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prose
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • swearing
  • brainstorm 40x
  • rp
  • llama3
  • llama-3
  • enhanced quants
  • max quants
  • maxcpu quants
  • horror
  • llama-cpp
  • gguf-my-repo

LoveGlaze/L3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated-Q4_K_M-GGUF

This model was converted to GGUF format from DavidAU/L3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo LoveGlaze/L3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated-Q4_K_M-GGUF --hf-file l3-darkest-planet-16b-heretic-uncensored-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo LoveGlaze/L3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated-Q4_K_M-GGUF --hf-file l3-darkest-planet-16b-heretic-uncensored-abliterated-q4_k_m.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo LoveGlaze/L3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated-Q4_K_M-GGUF --hf-file l3-darkest-planet-16b-heretic-uncensored-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo LoveGlaze/L3-Darkest-Planet-16B-HERETIC-Uncensored-Abliterated-Q4_K_M-GGUF --hf-file l3-darkest-planet-16b-heretic-uncensored-abliterated-q4_k_m.gguf -c 2048

README history 1 version

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

  1. 2026-01-01Upload README.md with huggingface_hub77c37bb2.6 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.

Open in Abliteration