← back to catalog · registered 2026-09-17 18:56

KW-KI/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF

KW-KI 9B GGUF multimodal second-order
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 · 30-day
0
Likes
0
Model age
today
created 2026-09-17

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 · 0 downloads combined

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

Metadata

License
apache-2.0
Languages
en zh
Tags
transformers gguf unsloth heretic uncensored abliterated fine tune creative creative writing fiction writing plot generation sub-plot generation

Related

Total size
5.09 GB
Files
3
Quantizations
1
Registered
2026-09-17 18:56
Last updated on HF
2026-09-17 18:18

Files by quantization

Auxiliary files 3 files 5.09 GB
qwen3.6-9b-heretic-uncensored-thinking-sweet-madness-q4_k_m.gguf 5.09 GB 9eceef9c download
README.md 2.57 KB a543725e download
.gitattributes 1.58 KB 2911c7c2 download

README current version from Hugging Face


language:

  • en
  • zh
    license: apache-2.0
    tags:
  • unsloth
  • heretic
  • uncensored
  • abliterated
  • fine tune
  • 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 prosing
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • all use cases
  • llama-cpp
  • gguf-my-repo
    library_name: transformers
    pipeline_tag: image-text-to-text
    base_model: DavidAU/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness

KW-KI/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF

This model was converted to GGUF format from DavidAU/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness 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 KW-KI/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF --hf-file qwen3.6-9b-heretic-uncensored-thinking-sweet-madness-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo KW-KI/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF --hf-file qwen3.6-9b-heretic-uncensored-thinking-sweet-madness-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 KW-KI/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF --hf-file qwen3.6-9b-heretic-uncensored-thinking-sweet-madness-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo KW-KI/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF --hf-file qwen3.6-9b-heretic-uncensored-thinking-sweet-madness-q4_k_m.gguf -c 2048
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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.