onyx-AI-Gemma4 0.1.3

Professional Multimodal AI Engine for Onyx platform

💎 ONYX AI Gemma 4 Engine (E2B Edition)

A high-performance, easy-to-use FastAPI wrapper for Gemma Multimodal models with built-in 4-bit quantization and streaming support. Developed by ONYX.

🚀 Features

• Zero Config Integration: Deploy a multimodal AI server in seconds.
• Optimized Performance: Native 4-bit quantization using bitsandbytes for low VRAM/RAM usage.
• Real-time Streaming: Built-in SSE (Server-Sent Events) for smooth, token-by-token generation.
• Hardware Friendly: Optimized for both GPU and high-performance CPU inference.

📦 Installation

You can install the engine directly via pip:

pip install onyx_AI_Gemma4

💻 Python Usage Guide
To use the library in your Python project, simply import the engine and run it. The engine handles model loading, quantization, and server routing automatically.

Python
from onyx_AI_Gemma4 import OnyxEngine

# 1. Initialize the Engine 
# It will automatically download and quantize the model on the first run.
engine = OnyxEngine(model_id="google/gemma-4-E2B-it")

# 2. Start the FastAPI Server
# The server will be available at http://localhost:7860
if __name__ == "__main__":
    print("🚀 Starting ONYX Engine...")
    engine.run(host="0.0.0.0", port=7860)
🛠 API Interaction
Once the server is running, you can interact with it using any HTTP client (like Postman or cURL):

Endpoint: POST /predict

Example Request:

JSON
{
  "messages": [
    {
      "role": "user", 
      "content": "Explain the importance of AI in modern software engineering."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024
}
🔗 Project Links
Organization: ONYX

Portfolio: Eng. Rawan Jassim

LinkedIn: Professional Profile

© 2026 ONYX. All rights reserved.