This is the Linux app named NVIDIA Personal AI Router (PAIR) whose latest release can be downloaded as service-binaries-linux-arm64.zip. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named NVIDIA Personal AI Router (PAIR) with OnWorks for free.
Follow these instructions in order to run this app:
- 1. Downloaded this application in your PC.
- 2. Enter in our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 3. Upload this application in such filemanager.
- 4. Start the OnWorks Linux online or Windows online emulator or MACOS online emulator from this website.
- 5. From the OnWorks Linux OS you have just started, goto our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 6. Download the application, install it and run it.
SCREENSHOTS:
NVIDIA Personal AI Router (PAIR)
DESCRIPTION:
NVIDIA Personal AI Router (PAIR) is a local inference router that distributes independent AI requests across compatible computers on the same network. It automatically discovers participating machines and routes jobs according to model availability, engine availability, and current workload. PAIR works with Ollama and LM Studio while exposing Ollama-compatible and OpenAI-compatible endpoints to applications and agents. Windows, Linux, and macOS systems can participate in the same cluster across x64 and Arm64 architectures. A desktop application manages nodes, engines, models, jobs, endpoints, and cluster pairing, while a terminal interface supports headless machines. PAIR keeps fully local configurations on the local network and is especially useful for concurrent workloads such as multi-agent applications. It routes each request to one machine rather than combining GPU memory or splitting a model across devices.
Features
- Automatic local-network node discovery
- Workload-aware AI inference routing
- Ollama and LM Studio engine support
- OpenAI-compatible and Ollama-compatible API endpoints
- Cross-platform Windows, Linux, and macOS clustering
- Desktop and terminal-based cluster management
Programming Language
Go
Categories
This is an application that can also be fetched from https://sourceforge.net/projects/nvidia-pair.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.