Instructions to use Thaurock/DeepSeek-R1-Distill-Qwen-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 Thaurock/DeepSeek-R1-Distill-Qwen-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 Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Thaurock/DeepSeek-R1-Distill-Qwen-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 Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Thaurock/DeepSeek-R1-Distill-Qwen-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 Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Thaurock/DeepSeek-R1-Distill-Qwen-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 Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Thaurock/DeepSeek-R1-Distill-Qwen-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": "Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M

Ollama
How to use Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF with Ollama:
```
ollama run hf.co/Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M
```

Lemonade

How to use Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Why this repository?

Unlike incomplete GGUF uploads, this repository provides the full 11-quantization spectrum (from high-precision F16 down to lightweight Q2_K) of the abliterated DeepSeek-R1-Distill-Qwen-32B model.

Choose the exact fit for your VRAM/RAM constraints without sacrificing reasoning capabilities.

DeepSeek-R1-Distill-Qwen-32B-abliterated - GGUF

This is the integral and complete collection of quantizations in GGUF format for the DeepSeek-R1-Distill-Qwen-32B-abliterated model, prepared locally for use with llama.cpp, Ollama, LM Studio, or Text-Generation-WebUI.

This model combines advanced reasoning distillation (deep logical thinking capability via <think> tags) based on Alibaba's powerful Qwen-32B model, but processed with abliteration techniques to root out artificial system censorship filters and blocks, responding without restrictions.

📋 Available Files (Complete Collection Without Splits)

File	Est. Size	BPW (Bits per Weight)	Recommended Usage Profile
`DeepSeek-R1-Distill-Qwen-32B-abliterated-F16.gguf`	~65.6 GB	16.00	Complete Base Template. Absolute fidelity of floating-point weights.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q8_0.gguf`	~34.8 GB	8.50	Identical quality to the original, ideal for maximizing performance on local hardware with high-end GPUs.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q6_K.gguf`	~27.2 GB	6.59	Extremely high retention of the logical reasoning tree with an optimized weight.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q5_K_M.gguf`	~23.4 GB	5.69	Recommended Sweet Spot. Keeps deep thinking coherence intact while critically reducing weight.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q5_K_S.gguf`	~22.8 GB	5.54	Compact 5-bit variant.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q4_K_M.gguf`	~19.9 GB	4.85	The Most Wanted. Optimal balance to run 32B reasoning inferences on advanced home setups.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q4_K_S.gguf`	~18.8 GB	4.58	Compact 4-bit variant to accelerate tokens-per-second speed.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q3_K_L.gguf`	~16.5 GB	4.01	Medium-high 3-bit compression. Retains basic reasoning capabilities.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q3_K_M.gguf`	~15.1 GB	3.66	Intermediate 3-bit variant.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q3_K_S.gguf`	~14.2 GB	3.44	Lightweight 3-bit variant.
`DeepSeek-R1-Distill-Qwen-32B-abliterated-Q2_K.gguf`	~12.1 GB	2.90	Extreme Compression. May experience minor issues in the internal structure of thinking tags. For experimental development only.

Note: Sizes are initial baseline estimates based on the model's native weight in safetensors (32.8B parameters); verifying the final size on disk after local compilation is recommended.

💡 Highlighted Usage

Since this is a distilled deep reasoning model, it is recommended to use a clean prompt format that respects the native chain-of-thought generation in your terminal:

./llama-cli -m DeepSeek-R1-Distill-Qwen-32B-abliterated-Q4_K_M.gguf -n 2048 -p "How does elliptic curve cryptography work?"

Usage Tip: If you notice the model skipping the <think> tag or attempting an initial refusal given an ambiguous prompt, you can guide the inference by providing a few-shot example or pre-filling the assistant's response with an opened <think> tag to force the restriction-free reasoning chain.

⚖️ Disclaimer

This model is open-access and lacks artificial safety filters due to the experimental abliteration process. The generated content and resulting logical reflections are the sole responsibility of the individual running the local inference.

🔒 Verificación de Integridad Sha256sum (SHA-256)

Para asegurarte de que los archivos de gran tamaño no se hayan corrompido durante la descarga, podés verificar su integridad utilizando el archivo oficial SHA256SUMS.txt provisto en este repositorio.

En Linux / macOS: Abre una terminal en la carpeta donde descargaste el modelo y el archivo de hashes, y ejecuta(EJEMPLO):

grep "DeepSeek-R1-Distill-Qwen-32B-abliterated-Q4_K_M.gguf" SHA256SUMS.txt | sha256sum -c

Resultado Esperado:

DeepSeek-R1-Distill-Qwen-32B-abliterated-Q4_K_M.gguf: La suma coincide (o OK) (¡Descarga perfecta!)

Resultado Negativo:

DeepSeek-R1-Distill-Qwen-32B-abliterated-Q4_K_M.gguf: "La suma NO coincide (¡Falla!) La descarga falló o está incompleta. Se recomienda volver a descargar ese archivo específico.

Nota: Si vas a verificar otro tamaño (como el Q5_K_M o el Q8_0), simplemente reemplaza el nombre del archivo dentro de las comillas del comando.

Credits

Base Distilled Model: deepseek-ai / Qwen (Alibaba Cloud)
Abliteration: huihui-ai
Complete GGUF Quantizations: Thaurock

Downloads last month: 1,187

GGUF

Model size

33B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Thaurock/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Finetuned

huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated

Quantized

(21)

this model