Instructions to use Qalbun-AI/QalbunLLM-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qalbun-AI/QalbunLLM-V1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Qalbun-AI/QalbunLLM-V1",
	filename="qalbun-base-models-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Qalbun-AI/QalbunLLM-V1 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 Qalbun-AI/QalbunLLM-V1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Qalbun-AI/QalbunLLM-V1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Qalbun-AI/QalbunLLM-V1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Qalbun-AI/QalbunLLM-V1: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 Qalbun-AI/QalbunLLM-V1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Qalbun-AI/QalbunLLM-V1: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 Qalbun-AI/QalbunLLM-V1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Qalbun-AI/QalbunLLM-V1:Q4_K_M

Use Docker

docker model run hf.co/Qalbun-AI/QalbunLLM-V1:Q4_K_M

LM Studio
Jan
Ollama
How to use Qalbun-AI/QalbunLLM-V1 with Ollama:
```
ollama run hf.co/Qalbun-AI/QalbunLLM-V1:Q4_K_M
```

Unsloth Studio

How to use Qalbun-AI/QalbunLLM-V1 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 Qalbun-AI/QalbunLLM-V1 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 Qalbun-AI/QalbunLLM-V1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Qalbun-AI/QalbunLLM-V1 to start chatting

How to use Qalbun-AI/QalbunLLM-V1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Qalbun-AI/QalbunLLM-V1: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": "Qalbun-AI/QalbunLLM-V1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Qalbun-AI/QalbunLLM-V1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Qalbun-AI/QalbunLLM-V1: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 Qalbun-AI/QalbunLLM-V1:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Qalbun-AI/QalbunLLM-V1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Qalbun-AI/QalbunLLM-V1: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 "Qalbun-AI/QalbunLLM-V1: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 Qalbun-AI/QalbunLLM-V1 with Docker Model Runner:
```
docker model run hf.co/Qalbun-AI/QalbunLLM-V1:Q4_K_M
```

Lemonade

How to use Qalbun-AI/QalbunLLM-V1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Qalbun-AI/QalbunLLM-V1:Q4_K_M

Run and chat with the model

lemonade run user.QalbunLLM-V1-Q4_K_M

List all available models

lemonade list

Qalbun AI

Qalbun AI is an innovative AI model designed to integrate Islamic principles with cutting-edge artificial intelligence. Built to respect and reflect traditional values while harnessing modern technology, Qalbun AI offers context-aware, ethical, and culturally aligned interactions.

Overview

Qalbun AI bridges the gap between timeless Islamic wisdom and state-of-the-art AI research. The model adapts to user inputs with a deep understanding of context, ensuring that each response honors the ethical and cultural dimensions of Islam.

Available Versions

Qalbun AI is offered in multiple deployment variants to meet diverse performance and resource requirements:

Full Precision (f32):
The most accurate version, providing the highest performance and complete model capabilities—ideal for research and critical applications.
Half Precision (f16):
A balanced variant that reduces memory usage while still delivering robust performance.
Quantized 8-bit (Q8):
An optimized model that significantly lowers memory consumption with a slight trade-off in accuracy.
Quantized 4-bit (Q4):
The most lightweight version, designed for resource-constrained environments while maintaining essential functionality.

Key Features

Ethical AI:
Developed with a commitment to Islamic ethics, Qalbun AI integrates core cultural values into every interaction.
Contextual Understanding:
Delivers intelligent, context-aware responses that respect both modern nuances and traditional teachings.
Interdisciplinary Integration:
Merges insights from AI research and Islamic studies to create a holistic, balanced approach to technology.
Continuous Learning:
Evolves over time by adapting to new research, user feedback, and emerging trends in both AI and ethical frameworks.

Releases

You can now run Qalbun AI offline on your phone! Download here

Author

Qalbun AI is developed and maintained by the Polyvor Labs Teams. Their multidisciplinary expertise in artificial intelligence and Islamic studies drives the innovation behind this project.