Instructions to use Solotovfahl/Arete-27B-Abliterated-Solotov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Solotovfahl/Arete-27B-Abliterated-Solotov 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 Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K
# Run inference directly in the terminal:
llama cli -hf Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K
# Run inference directly in the terminal:
llama cli -hf Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K
# Run inference directly in the terminal:
./build/bin/llama cli -hf Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

Use Docker

docker model run hf.co/Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

Llama new
LM Studio
Jan

vLLM

How to use Solotovfahl/Arete-27B-Abliterated-Solotov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Solotovfahl/Arete-27B-Abliterated-Solotov"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Solotovfahl/Arete-27B-Abliterated-Solotov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

Ollama
How to use Solotovfahl/Arete-27B-Abliterated-Solotov with Ollama:
```
ollama run hf.co/Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K
```
Unsloth Desktop

How to use Solotovfahl/Arete-27B-Abliterated-Solotov with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Solotovfahl/Arete-27B-Abliterated-Solotov with Docker Model Runner:
```
docker model run hf.co/Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K
```

Lemonade

How to use Solotovfahl/Arete-27B-Abliterated-Solotov with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

Run and chat with the model

lemonade run user.Arete-27B-Abliterated-Solotov-Q6_K

List all available models

lemonade list

Hermes Agent

How to use Solotovfahl/Arete-27B-Abliterated-Solotov with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

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 Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Solotovfahl/Arete-27B-Abliterated-Solotov with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K

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 "Solotovfahl/Arete-27B-Abliterated-Solotov:Q6_K" \
  --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"

Arete-27B-Abliterated-Solotov (GGUF Q6_K)

An abliterated (refusal-direction removed) GGUF quant of NousResearch/Arete-27B, which is itself a post-train of Qwen/Qwen3.8-27B.

GitHub (Modelfile & docs): https://github.com/brendonfahlusa/Arete-27B-Abliterated-Solotov

Credits

Nous Research for Arete-27B (Apache-2.0).
Alibaba Qwen team for Qwen3.8-27B (Apache-2.0).
Abliteration recipe follows the approach used by huihui-ai's Qwen3.8-27B abliterated model.

Modifications (Apache-2.0 §4 notice)

The weights of Arete-27B were modified by a static abliteration transform. For each decoder layer 18–51 (inclusive), the output projections were left-projected to remove a unit "refusal direction" d in the 5120-dim hidden space:

W' = W - d (dᵀ W)

applied to mlp.down_proj.weight, self_attn.o_proj.weight (full-attention layers) and linear_attn.out_proj.weight (linear-attention layers). The first 18 and last 12 layers are untouched. The result was converted to GGUF f16 and quantized to Q6_K (~22.1 GB).

⚠️ Disclaimer

This model is uncensored: its safety refusals have been largely removed. It may produce harmful, offensive, or inaccurate content. You are solely responsible for how you use it and for complying with applicable laws. Not intended for deployment to end users without your own safeguards. Provided "AS IS" without warranty.

Performance (tested)

RTX 5090 (32 GB), fully on GPU: ~57 tok/s
Context: 64k (num_ctx 65536)
Chat and tool calling verified with Ollama

Ollama

FROM ./Arete-27B-Abliterated-Solotov-Q6_K.gguf
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER temperature 1
PARAMETER top_k 20
PARAMETER top_p 0.95
PARAMETER min_p 0
PARAMETER num_ctx 65536

ollama create arete-27b-abliterated -f Modelfile
ollama run arete-27b-abliterated

License

Apache-2.0, same as the base model. See LICENSE.

Downloads last month: 473

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

6-bit

Model tree for Solotovfahl/Arete-27B-Abliterated-Solotov

Base model

Qwen/Qwen3.8-27B

Finetuned

NousResearch/Arete-27B

Quantized

(46)

this model