← All news·2026-09-03·3 min read

Nvidia PAIR: Connect your home PCs to a local AI cluster

Nvidia introduced its Personal AI Router (PAIR), an open-source and free program allowing users to form a local AI cluster using home devices. It works with GeForce RTX 20 series GPUs, Apple M4, and is available since September 3.

nvidiainferencelocal-aiopen-source

Nvidia introduced its Personal AI Router (PAIR), an open-source and free program allowing users to form a local AI cluster using home devices. PAIR is a software solution that helps detect other devices on a local network that are able to perform AI computations, splitting tasks between them and performing AI inference locally without transferring user data to the cloud.

What PAIR Can Do

It can be used with Ollama and LM Studio, popular apps that allow you to run AI locally. PAIR splits heavy tasks into smaller ones and executes them in parallel across different devices, so if someone starts playing a game and occupies the graphics card, the application will redistribute the load. All devices communicate over an encrypted channel using mTLS with a six-digit code for the initial setup.

Compatibility

PAIR works with Nvidia GeForce RTX GPUs from the 20 series, RTX Pro, DGX Spark, Apple M4, and other. It is available for Windows, Linux, and macOS operating systems. The beta version was launched on September 3, 2026.

Nvidia claims there is a lot of untapped power in the average American household. For example, the company says that a typical family owns an RTX Spark laptop, DGX Spark desktop, RTX 5090 laptop, a gaming desktop, and a MacBook Pro, which adds up to approximately 165 teraflops, which is rarely used for AI at a particular time. Three app partners Perplexity Portable Computer, Hermes Agent, and OpenClaw are changing their configurations to support PAIR.

Source: www.theverge.com

Free course

Stop reading about AI — start building with it

The free Claude Code course: your first site, tool or game — no coding. No upsells, no cross-sells — nothing to buy here.

Start free →
EAEvgenii Arsentev

Author

Evgenii Arsentev

PhD · Chief Executive Officer, digital health