Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
Help Center
Getting Started
  1. Create and verify your account to unlock full access to NVIDIA NIM APIs.
ResourcesDeveloper ForumsContact Support
FAQs
  • Install and Use NVIDIA PAIR

    10 MIN

    Run local AI requests through PAIR and route independent Ollama or LM Studio requests across compatible systems.

    • DGX Spark
    • Inference
    • LM Studio
    • Multi-Node
    • Ollama
    • RTX
    • RTX PRO
    Explore NVIDIA Playbooks
    OverviewOverviewSet Up the PAIR AppSet Up the PAIR AppSet Up PAIR with TerminalSet Up PAIR with TerminalTroubleshootingTroubleshooting

    Troubleshooting

    Start with the symptom and then inspect Settings → Service, the desktop error surface, or the terminal interface's Errors tab for more detail.

    SymptomUsual meaningWhat to do
    PAIR remains on Loading...A background service did not start correctly.Wait one or two minutes, then inspect Settings → Service and restart the affected service.
    A node is not discoveredmDNS is blocked or unavailable.Confirm both nodes are on the same trusted local network, allow 5353/udp, or add the node by IP address.
    Pairing stalls or failsThe invitation expired, the PIN is incorrect, or port 14321 is blocked.Start a new invitation, enter the new PIN, and confirm cluster ports are reachable.
    Connection refusedNothing is listening at that address.Copy the current URL from Endpoints and confirm the PAIR service is running.
    403 from another machinePAIR endpoints accept loopback traffic only.Run PAIR on the machine hosting the client and use its local endpoint.
    502 with no active nodeNo node is eligible for the request.Start a compatible engine and make the requested model available on at least one online node.
    Persistent 404 on inferenceNo eligible node has the requested model.Verify the exact model name and prepare it on at least one node.
    400 or 422The request is malformed.Correct its JSON, route, model name, or required fields; malformed requests are not retried.
    A response arrives but Jobs is emptyAnother process owns the expected proxy port.Check Endpoints and Settings → Service, then change the PAIR port or stop the conflicting process.
    Requests do not use every GPUPAIR routes each request to one eligible node.Send independent requests and verify Ran on for each job. PAIR does not split one request across GPUs.
    Desktop and terminal behavior conflictsBoth PAIR interfaces are running on one system.Stop one interface and use only the desktop application or terminal interface.

    Resources

    • NVIDIA Personal AI Router Releases
    • DGX Spark Documentation
    • Ollama Documentation
    • LM Studio Documentation
    Terms of Use
    Privacy Policy
    Your Privacy Choices
    Contact

    Copyright © 2026 NVIDIA Corporation