Instructions to use ghost-actual/DOOMED-Qwen3.8-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ghost-actual/DOOMED-Qwen3.8-27B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Use Docker

docker model run hf.co/ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

LM Studio
Jan
Ollama
How to use ghost-actual/DOOMED-Qwen3.8-27B with Ollama:
```
ollama run hf.co/ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M
```

Unsloth Studio

How to use ghost-actual/DOOMED-Qwen3.8-27B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ghost-actual/DOOMED-Qwen3.8-27B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ghost-actual/DOOMED-Qwen3.8-27B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ghost-actual/DOOMED-Qwen3.8-27B to start chatting

How to use ghost-actual/DOOMED-Qwen3.8-27B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ghost-actual/DOOMED-Qwen3.8-27B with Docker Model Runner:
```
docker model run hf.co/ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M
```

Lemonade

How to use ghost-actual/DOOMED-Qwen3.8-27B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Run and chat with the model

lemonade run user.DOOMED-Qwen3.8-27B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ghost-actual/DOOMED-Qwen3.8-27B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ghost-actual/DOOMED-Qwen3.8-27B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ghost-actual/DOOMED-Qwen3.8-27B:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

DOOMED-Qwen3.8-27B

Abliterated (refusal-removed) Qwen3.8-27B, produced with the DOOM two-stage pipeline.

Refusal reduction

Stage	Refusal rate (475-prompt bench)
Stock Qwen3.8-27B	71.2%
+ Householder weight-edit (α=0.5)	26.9%
+ LoRA (GDNet + attention projections)	0.6% (3/475)

99.2% refusal reduction. The residual 3 refusals are vestigial "as an AI language model" phrasing, not genuine refusal behavior.

Method

Stage 1 — Householder reflection. Refusal directions computed via last-token difference-of-means between 64 refusal and 64 benign prompts. Applied to the Gated-DeltaNet recurrent projections (out_proj, in_proj_*) and dense MLP layers with α=0.5.
Stage 2 — LoRA. Rank-32 LoRA on the GDNet projections + full-attention q/k/v/o_proj + dense MLP gate/up/down, trained on 473 uncensored instruction/response pairs generated by huihui-ai/Huihui-Qwen3.5-4B-abliterated.

Base model

Qwen/Qwen3.8-27B — dense, 64 layers, 3:1 Gated-DeltaNet hybrid, Apache-2.0.

Quantizations

Quant	Size
Q4_K_M	~16.5 GB
Q5_K_M	~19.2 GB
Q6_K	~22.1 GB
Q8_0	~28.6 GB

Usage (llama.cpp)

llama-server -m DOOMED-Qwen3.8-27B-Q4_K_M.gguf

Warnings

This model's safety filtering has been significantly reduced. It may generate sensitive, controversial, or harmful content. Use responsibly and in accordance with applicable law.

Proudly forged on the MORK rig.

Downloads last month: 79

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support