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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

preview code

Raw

History Blame

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`](https://huggingface.co/TobiasLogic/Qwen2.5-Coder-32B-abliterated),
	an abliterated (uncensored) build of
	[`Qwen/Qwen2.5-Coder-32B-Instruct`](https://huggingface.co/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](https://github.com/evalplus/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.

	![Coding benchmarks: pass@1](https://raw.githubusercontent.com/TobiasLogic/Qwen2.5-Coder-Abliterate/main/benchmark_chart.png)

	\| 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.

	<sub>Base numbers: Qwen2.5-Coder-32B-Instruct, [tech report](https://arxiv.org/abs/2409.12186) Table 16. Measured 2026-07, Q4_K_M via Ollama.</sub>

	## Usage

	Ollama (a `Modelfile` is included in this repo):

	```bash
	# 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:

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

	## Links

	- fp16 weights: [`TobiasLogic/Qwen2.5-Coder-32B-abliterated`](https://huggingface.co/TobiasLogic/Qwen2.5-Coder-32B-abliterated)
	- Reproducible pipeline: [github.com/TobiasLogic/Qwen2.5-Coder-Abliterate](https://github.com/TobiasLogic/Qwen2.5-Coder-Abliterate)

	## License

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