NVIDIA Personal AI Router (PAIR) connects computers on your local network and presents Ollama-compatible and OpenAI-compatible proxy endpoints to applications and agents. It automatically routes each independent AI inference request to an eligible computer according to engine availability, model availability, and current workload. Run PAIR on one computer for local inference, or run it on several computers to handle more requests.
PAIR is useful for workloads such as multi-agent applications that make several requests at once. PAIR is designed to keep prompts and responses on your local network when the application, model source, engine, and paired computers are all local.
IMPORTANT
PAIR sends each request to one system. It does not combine GPU memory, join GPUs into one larger GPU, or split a model or request across systems.
You'll install PAIR, prepare an engine and model, and send a test request through PAIR's local endpoint.
You can also pair trusted systems and route independent requests to systems that have the requested model.
Required:
Optional:
Use one PAIR interface at a time. Do not run the desktop application and the terminal interface on the same system. They start competing services and can conflict over ports, engines, and settings.
PAIR accepts requests only from the local system. Install PAIR on the system where your application runs. That system can use an engine on another cluster node, so it does not need its own GPU or inference engine.
Read the PAIR security policy before you use PAIR on a shared or untrusted network.
Use the matrix below to confirm your hardware platform, operating system, memory, and whether you can use it in a PAIR cluster.
| Hardware platform | OS | Memory | Multi-node capable hardware |
|---|---|---|---|
| DGX Spark | DGX OS (Linux) | 128 GB Unified Memory | ✅ (PAIR cluster) |
| NVIDIA GeForce RTX 20 Series or newer; NVIDIA RTX PRO (Turing or newer) | Windows 11 or Linux | Depends on the GPU and model | ✅ (PAIR cluster) |
DGX Spark, NVIDIA GeForce RTX, and NVIDIA RTX PRO are the hardware platforms covered by this playbook. PAIR can also pair compatible systems that run the supported operating systems below.
| Support | Details |
|---|---|
| Operating systems | Windows 11, Linux, and macOS |
| Architectures | x64 and arm64 on all three operating systems. Windows on ARM is experimental. |
| Installers | Windows .exe, Linux .deb, and macOS .dmg. Build from source for other Linux distributions. |
| Mixing systems | Windows, Linux, and macOS systems can pair with each other. |
| Inference engines | Ollama and LM Studio |
Check the PAIR releases page for a package for your operating system and architecture.
Hardware requirements
Software requirements
PAIR can run on a supported system even when an engine cannot. Each engine has its own requirements for the operating system, GPU, and drivers. Each model also needs enough memory to load. Check the engine documentation before you expect a system to serve a model.
No extra files are required.
For a graphical setup, open Set Up the PAIR App. For a headless or SSH setup, open Set up PAIR with Terminal.