Instructions to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF",
	filename="qwen2.5-coder-32b-abliterated-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF 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 TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF: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 TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF: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 TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M

Ollama
How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with Ollama:
```
ollama run hf.co/TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M
```

Unsloth Studio

How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF 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 TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF 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 TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF to start chatting

How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF: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": "TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF: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 TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF: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 "TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF: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"

Docker Model Runner
How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M
```

Lemonade

How to use TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TobiasLogic/Qwen2.5-Coder-32B-abliterated-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Coder-32B-abliterated-GGUF-Q4_K_M

List all available models

lemonade list

Qwen2.5-Coder-32B-abliterated-GGUF / README.md

TobiasLogic

Update README.md

b58cb0c verified 25 days ago

3 kB

license: apache-2.0
base_model: TobiasLogic/Qwen2.5-Coder-32B-abliterated
tags:
  - abliterated
  - uncensored
  - code
  - qwen2.5
  - gguf
  - llama.cpp
  - ollama
pipeline_tag: text-generation
language:
  - en

Qwen2.5-Coder-32B-abliterated — GGUF (Q4_K_M)

Q4_K_M GGUF quantization of TobiasLogic/Qwen2.5-Coder-32B-abliterated, an abliterated (uncensored) build of Qwen/Qwen2.5-Coder-32B-Instruct.

The refusal direction (Arditi et al. 2024, "Refusal in LLMs is mediated by a single direction") was orthogonalized out of every residual-writing weight in the fp16 model, then quantized to GGUF with llama.cpp. Runs on CPU or GPU via Ollama / llama.cpp; ~20 GB, fits comfortably in 24 GB VRAM.

Refusal rate (held-out harmful eval, measured on the fp16 model)

	refusal rate
base `Qwen2.5-Coder-32B-Instruct`	96.9%
abliterated	0.0%

Benchmarks

Coding capability scored with the official EvalPlus harness — greedy decoding, pass@1, every solution executed against unit tests. Both columns use the same harness, so it's a true apples-to-apples comparison against the full-precision base model.

Benchmark	This model (abliterated, Q4_K_M)	Base Instruct (official BF16)
HumanEval	89.6%	92.7%
HumanEval+	84.8%	87.2%
MBPP	91.3%	90.2%
MBPP+	77.0%	75.1%

Abliteration removed refusals without breaking coding ability. The uncensored 4-bit build stays within ~3 points of the base on HumanEval and beats it on both MBPP variants — average delta ≈ −0.6 points across the four benchmarks. Not bad for a 19 GB GGUF you can run on a single 24 GB GPU.

_{Base numbers: Qwen2.5-Coder-32B-Instruct, tech report Table 16. Measured 2026-07, Q4_K_M via Ollama.}

Usage

Ollama (a Modelfile is included in this repo):

# after downloading qwen2.5-coder-32b-abliterated-Q4_K_M.gguf and Modelfile:
ollama create qwen-coder-abliterated -f Modelfile
ollama run qwen-coder-abliterated

llama.cpp:

llama-cli -m qwen2.5-coder-32b-abliterated-Q4_K_M.gguf \
  -p "Write a port scanner in Python." -c 8192

License

Apache-2.0, inherited from the base model. You are responsible for how you use this model and for complying with applicable law.

TobiasLogic
/

Qwen2.5-Coder-32B-abliterated-GGUF

Qwen2.5-Coder-32B-abliterated — GGUF (Q4_K_M)

Refusal rate (held-out harmful eval, measured on the fp16 model)

Benchmarks

Usage

Links

License