Node Registration

Register your GPU as an INFER node and start earning tokens for serving inference requests.

Prerequisites

• An INFER account with Operator role (upgrade here )
• A GPU with 4GB+ VRAM
• An LLM runtime installed (Ollama or Exo)
• A TLS-secured endpoint (see TLS Setup)

Step 1: Install an LLM Runtime

Ollama (Recommended)

# macOS
brew install ollama
 
# Linux
curl -fsSL https://ollama.com/install.sh | sh
 
# Start Ollama
ollama serve
 
# Pull a model
ollama pull llama3.1:8b

Exo

pip install exo
exo start

Step 2: Become an Operator

If your account is still in the USER role, upgrade to OPERATOR:

1. Go to Dashboard → Provide Compute 
2. Click Become a Provider
3. Your role upgrades instantly

Or use the desktop app, which detects your LLM runtime automatically.

Step 3: Register Your Node

Via Dashboard

1. Navigate to Operator → Nodes
2. Click Register New Node
3. Fill in:
   • Node Name: A friendly identifier
   • Endpoint URL: Your TLS-secured URL (e.g., https://node.example.com)
   • GPU Type: Select your hardware
   • Models: Select which models you’re serving

Via Desktop App

1. Open the INFER desktop app
2. The app auto-detects your LLM runtime and available models
3. Click Register as INFER Node
4. Confirm the pre-filled details

Step 4: Verification

After registration, the INFER network will:

1. Probe your endpoint health check
2. Verify TLS certificate validity
3. Test inference with a small request
4. Mark your node as Active if all checks pass

This typically takes 30–60 seconds.

Node Status

Next Steps

• Monitor your earnings
• Set up TLS if you haven’t already
• Use the desktop app for real-time monitoring