Instructions to use theBOrg32/Egyptian_qwen_mobile_version with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theBOrg32/Egyptian_qwen_mobile_version with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="theBOrg32/Egyptian_qwen_mobile_version",
	filename="egyptian_qwen_model_q2.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use theBOrg32/Egyptian_qwen_mobile_version with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theBOrg32/Egyptian_qwen_mobile_version
# Run inference directly in the terminal:
llama-cli -hf theBOrg32/Egyptian_qwen_mobile_version

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theBOrg32/Egyptian_qwen_mobile_version
# Run inference directly in the terminal:
llama-cli -hf theBOrg32/Egyptian_qwen_mobile_version

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 theBOrg32/Egyptian_qwen_mobile_version
# Run inference directly in the terminal:
./llama-cli -hf theBOrg32/Egyptian_qwen_mobile_version

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 theBOrg32/Egyptian_qwen_mobile_version
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theBOrg32/Egyptian_qwen_mobile_version

Use Docker

docker model run hf.co/theBOrg32/Egyptian_qwen_mobile_version

LM Studio
Jan
Ollama
How to use theBOrg32/Egyptian_qwen_mobile_version with Ollama:
```
ollama run hf.co/theBOrg32/Egyptian_qwen_mobile_version
```

Unsloth Studio new

How to use theBOrg32/Egyptian_qwen_mobile_version 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 theBOrg32/Egyptian_qwen_mobile_version 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 theBOrg32/Egyptian_qwen_mobile_version to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theBOrg32/Egyptian_qwen_mobile_version to start chatting

Pi new

How to use theBOrg32/Egyptian_qwen_mobile_version with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf theBOrg32/Egyptian_qwen_mobile_version

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": "theBOrg32/Egyptian_qwen_mobile_version"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use theBOrg32/Egyptian_qwen_mobile_version with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf theBOrg32/Egyptian_qwen_mobile_version

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 theBOrg32/Egyptian_qwen_mobile_version

Run Hermes

hermes

Docker Model Runner
How to use theBOrg32/Egyptian_qwen_mobile_version with Docker Model Runner:
```
docker model run hf.co/theBOrg32/Egyptian_qwen_mobile_version
```

Lemonade

How to use theBOrg32/Egyptian_qwen_mobile_version with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theBOrg32/Egyptian_qwen_mobile_version

Run and chat with the model

lemonade run user.Egyptian_qwen_mobile_version-{{QUANT_TAG}}

List all available models

lemonade list

🇸🇾 Egyptian_Qwen-3.5-GGUF: Egyptian Dialect LLM for Edge & Mobile

🌟 Introduction

Run Egyptian Dialect AI anywhere — on your phone, tablet, or edge device.

We are proud to present Egyptian_Qwen-3.5-GGUF, the quantized, portable version of the first Large Language Model fine-tuned specifically for the Egyptian Arabic Dialect.

Built on Qwen 3.5 and converted to the GGUF format, this model brings authentic Egyptian Arabic understanding to resource-constrained environments — no cloud required, no data leaving your device.

🚀 Key Features

🗣️ Native Egyptian Dialect: Trained on colloquial Egyptian data, not just Modern Standard Arabic.
📱 PocketPal Ready: Optimized for seamless integration with PocketPal APK on Android.
⚡ Efficient Inference: Powered by llama.cpp backend for fast, low-memory CPU execution.
🔓 Open & Shareable: CC-BY-SA-4.0 licensed to foster community growth.

📱 How to Run on Mobile with PocketPal APK

A step-by-step walkthrough will be uploaded here shortly showing:

Downloading PocketPal APK from the official source
Importing the Egyptian_Qwen-3.5-GGUF model file
Configuring context length, temperature, and system prompt for Egyptian dialect
Starting your first offline conversation in Egyptian Arabic

Check the Video on how to run it on your smartphone

Quick Setup Guide (Text)

Install PocketPal APK on your Android device.
Download this model from the Files tab many version are available.
Open PocketPal → Models → "+" → Load Model from local → Select the downloaded .gguf file.
Start chatting fully offline, fully Egyptian.

⚠️ Ensure your device has at least 8GB RAM for Q4 quantizations. Close background apps for best performance.

⚖️ License & Commercial Use

We believe in open, shareable AI. This model is released under CC-BY-SA-4.0 to ensure derivatives remain open and community-driven.

✅ You Can:

Use, modify, and distribute this model in open-source projects (with attribution).
Use it commercially if your derivative work remains open-source under CC-BY-SA-4.0.

🔒 For Closed-Source / Proprietary Use:

If you plan to integrate this model (or a fine-tuned version) into a closed product, please contact us first:

📧 Licensing Inquiries: info2@the-borg.ru

🙏 Credits & Acknowledgments

This project stands on the shoulders of incredible open-source work:

🧠 Base Model: Qwen 3.5 by Alibaba Cloud
⚙️ GGUF Conversion & Runtime: llama.cpp
📱 Mobile Integration Reference: PocketPal APK
🛠️ Fine-Tuning & Alignment: The Borg Organization
📚 Dataset: Curated Egyptian Dialect Corpus

Citation

If you use Egyptian_Qwen-3.5-GGUF in your work, please cite:

@misc{Egyptian_qwen_gguf_2026,
  title={Egyptian_Qwen-3.5-GGUF: Portable Egyptian Dialect Large Language Model},
  author={The Borg Organization},
  year={2026},
  howpublished={\url{https://huggingface.co/theBOrg32/Egyptian_qwen_mobile_version}},
  license={CC-BY-SA-4.0}
}

Downloads last month: 11

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Collection including theBOrg32/Egyptian_qwen_mobile_version

Egyptian_Qwen3.5

Collection

4 items • Updated Mar 14