Guides to Deploy on Spheron

Comprehensive deployment guides for running AI nodes and large language models on Spheron.

Available Deployment Guides

🤖 AI Nodes

Deploy and run specialized AI network nodes:

Gonka AI Node

Deploy Gonka AI node infrastructure for decentralized AI workloads.

Pluralis Node 0

Set up and run Pluralis Node 0 for distributed AI network participation.

Inference Devnet Node

Deploy inference devnet nodes for AI model serving infrastructure.

Gensyn AI Node

Run Gensyn AI nodes for decentralized machine learning network.

🧠 Large Language Models (LLMs)

Deploy and run production-ready LLMs:

Qwen3-Omni-30B-A3B

Multimodal AI model with 30B parameters supporting text, audio, and vision inputs.

Qwen3-VL 4B & 8B

Vision-language models in 4B and 8B parameter versions for image understanding.

Chandra OCR

Specialized OCR model for document processing and text extraction.

Soulx Podcast-1.7B

Compact 1.7B parameter model optimized for podcast and audio content generation.

Janus CoderV-8B

Code generation and understanding model with 8B parameters.

Baidu Ernie-4.5-VL-28B-A3B

Advanced vision-language model from Baidu with 28B parameters.

Getting Started

Before deploying models or nodes:

1. Ensure you have an active Spheron AI account
   • See Getting Started if you're new
2. Check GPU requirements
   • Each guide lists minimum GPU specifications
   • See Platform Overview for available GPUs
3. Review pricing
   • Check Billing for cost information
   • Consider Reserved GPUs for long-term deployments
4. Understand resource needs
   • VRAM requirements vary by model size
   • Storage needs depend on model and dataset size
   • Network bandwidth for multi-node setups

Deployment Types

Quick Deploy

Most guides include quick deployment options:

• Pre-configured instances
• One-click setup scripts
• Automated environment setup

Custom Deployment

For advanced users:

• Manual configuration
• Custom model parameters
• Fine-tuning options
• Multi-GPU setups

Production Deployment

Enterprise-ready configurations:

• High-availability setups
• Load balancing
• Monitoring and logging
• Auto-scaling considerations

Common Requirements

Hardware

• GPU: Varies by model (RTX 4090 minimum for most)
• VRAM: 16GB-80GB depending on model
• Storage: 50GB-500GB for models and data
• RAM: 32GB+ recommended

Software

• OS: Ubuntu 22.04 LTS (recommended)
• CUDA: 11.8+ or 12.x
• Python: 3.9-3.11
• Docker: Optional but recommended

Network

• Stable internet connection
• Open ports for API access
• Sufficient bandwidth for data transfer

Support

Need help with deployment?

• Documentation: Each guide has detailed step-by-step instructions
• Community: Join Discord for help
• Quick Start: See Quick Start for basic deployment
• Connection Guides: Check Connecting to Instances for access methods

Additional Resources

• Security Best Practices - Secure your deployments
• SSH Connection - Connect to your instances
• Jupyter Notebook - Interactive development
• API Reference - Automate deployments

Choose a deployment guide above to get started with your AI workload on Spheron.