Instructions to use rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-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 rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-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 rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0
# Run inference directly in the terminal:
llama cli -hf rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0
# Run inference directly in the terminal:
llama cli -hf rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0

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 rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0
# Run inference directly in the terminal:
./llama-cli -hf rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0

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 rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0

Use Docker

docker model run hf.co/rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0

LM Studio
Jan
Ollama
How to use rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF with Ollama:
```
ollama run hf.co/rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0
```
Unsloth Desktop
Docker Model Runner
How to use rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF with Docker Model Runner:
```
docker model run hf.co/rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0
```

Lemonade

How to use rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF:Q5_0

Run and chat with the model

lemonade run user.DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF-Q5_0

List all available models

lemonade list

Atomic Chat

Model name: DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF

Format: GGUF Quantization: Q5_0 Base model: DeepSeek-R1-0528 / Qwen3-8B Converted by: rim89987

📌 Description

This is a GGUF-converted and quantized version of the DeepSeek-R1-0528 Qwen3-8B abliterated model. The model is optimized for local and lightweight inference using llama.cpp and compatible runtimes.

The Q5_0 quantization offers a strong balance between performance, speed, and memory efficiency, making it suitable for systems with limited VRAM or free cloud environments (e.g., Colab, Kaggle).

🚀 Use Cases

General chat & assistant tasks

Reasoning and logical responses

Coding assistance (light to medium)

Local LLM experiments

GGUF-based inference pipelines

⚙️ Compatibility

llama.cpp

llama-cpp-python

Ollama (GGUF support)

Text-generation-webui (llama backend)

💾 System Requirements (Approx.)

RAM / VRAM: ~6–7 GB

Recommended for CPU or low-end GPU setups

🧾 Credits

Original model: DeepSeek / Qwen

GGUF conversion & quantization: rim89987

Downloads last month: 68

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

5-bit

Inference Providers NEW

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

Model tree for rim89987/DeepSeek-R1-0528-Qwen3-8B-abliterated-Q5_0-GGUF

Base model

deepseek-ai/DeepSeek-R1

Quantized

(71)

this model