← back to catalog · registered 2026-09-19 00:56

alst10/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU

alst10 27B GGUF second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/alst10%2FQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU"
Response includes
  • classification m3
  • files 3
  • author_summary 2 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 · 30-day
0
Likes
0
Model age
today
created 2026-09-19

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

License
cc-by-4.0
Quantizations
Q4
Tags
gguf rocm rocmfpx amd llama.cpp base_model:DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU base_model:quantized:DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU license:cc-by-4.0 endpoints_compatible region:us conversational

Related

Total size
13.6 GB
Files
3
Quantizations
2
Registered
2026-09-19 00:56
Last updated on HF
2026-09-19 00:49

Files by quantization

Q4 1 file 13.6 GB
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-Q4_0_ROCMFP4_FAST.gguf 13.6 GB a058a1b4 download
Auxiliary files 2 files 3.21 KB
.gitattributes 1.61 KB 2463c9d1 download
README.md 1.60 KB 9d56fbcd download

README current version from Hugging Face


license: cc-by-4.0
base_model: DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
tags:

  • gguf
  • rocm
  • rocmfpx
  • amd
  • llama.cpp

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU - ROCmFPX Quantized

This model was dynamically quantized and generated using the ROCmFPX My Repo Space

Usage Instructions with ROCmFPX llama.cpp

To run this model, you must use the specialized ROCmFPX fork of llama.cpp by charlie12345. Standard llama.cpp releases do not currently support ROCmFPX quantization formats.

# 1. Clone the ROCmFPX repository
git clone --depth 1 [https://github.com/charlie12345/ROCmFPX.git](https://github.com/charlie12345/ROCmFPX.git)
cd ROCmFPX

# 2. Build the project
cmake -B build -G Ninja -DGGML_CUDA=OFF -DGGML_NATIVE=OFF
cmake --build build --target llama-cli -j

# 3. Run the model
./build/bin/llama-cli -m Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-Q4_0_ROCMFP4_FAST.gguf -p "You are a helpful assistant. Hello!" -n 128

License

This model is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. Please adhere to the original license constraints of the base model and provide appropriate attribution when sharing.

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.