Key points
- Free Nvidia tool routes AI inference across computers on a home network
- Three-device cluster cut an 18-minute agent job to 8:48
- RTX Spark Windows PCs arrive in October
On Thursday, September 3, at IFA 2026, Nvidia (NVDA) released PAIR, a free open-source tool that discovers compatible computers running PAIR on a home network and routes inference requests to machines with available capacity.
The name is short for Personal AI Router, and Nvidia calls it a virtual inference router. An agent running on one machine points at PAIR the way it would point at a local model server, and PAIR decides which computer on the network actually answers. Compatible agent software doesn't need a new integration. The target is inference, the running of a trained model rather than the training of one, which now accounts for more spending than model training.
PAIR does not combine the GPUs or their memory, and it cannot split one model request across several machines. Each request runs from start to finish on one node. The speedup comes when an agent generates several independent requests that can run at the same time. In Nvidia's own words, PAIR does not "merge GPUs or pool VRAM into one larger accelerator" and does not "shard a single model or split one inference request across machines."
The beta runs on Windows, macOS, and Linux, in both graphical and terminal versions. It supports GeForce RTX 20 Series cards and newer, RTX PRO workstation cards from the Turing generation on, the DGX Spark desktop, and Apple silicon from the M4 forward. The Apple line means a cluster doesn't have to be all Nvidia hardware.
Machines don't enlist themselves. PAIR discovers candidates over mDNS, and Nvidia said all traffic between two nodes stays blocked until a pairing is approved. Once the connection is made, communication between the nodes is encrypted with mTLS and generated certificates.
After that the cluster is elastic. A node contributes capacity when it has some and drops away when it powers down or hibernates. Nvidia lists five things PAIR weighs before it hands a job to a node:
- whether the node is online and ready
- whether a supported inference engine is enabled on it
- whether the exact model requested is already there
- how much work it is already doing
- how hard its GPU is being pushed by whatever else is open
The models don't have to match across the cluster, because PAIR can route a request to the machine that happens to hold the one it needs.
Nvidia published one measurement in a five-subagent workload run on Qwen 3.6 35B A3B. On a single RTX Spark laptop, the job took 18 minutes on average. On a three-device cluster of an RTX Spark laptop, a DGX Spark, and an RTX 5090, it took 8 minutes and 48 seconds. Nvidia labels that an "unofficial, configuration-specific demo, not a general benchmark or a promise of linear scaling," and says results depend on how parallel the workload is, along with the model, the engine settings, the hardware, the network, and which nodes are free.
What else Nvidia announced for local AI
Nvidia said llama.cpp now delivers "up to 1.9x higher throughput" on a GeForce RTX 5090, through kernel optimizations, improved speculative decoding, and faster prefill. Those gains are available directly and through LM Studio and Ollama.
Three agent applications are getting simpler setup on RTX hardware. Hermes Agent adds one-click configuration on Windows that detects the installed GPU, selects a model, and runs it through a tuned llama.cpp build. OpenClaw is getting a Windows app for standing up a local model on any RTX GPU with at least 24GB of video memory. Perplexity Portable Computer becomes available in September on RTX GPUs with at least 24GB of video memory running Linux.
The compact RTX Spark Windows PCs are due in October. Acer showed a desktop RTX Spark concept at the show, and Lenovo announced the Yoga Pro 9n and the Yoga 9n 2-in-1.
PAIR isn't a product Nvidia sells. Its source code is published under the Apache 2.0 license at github.com/NVIDIA/Personal-AI-Router and the software is in beta. What it does for the company is make the RTX cards and DGX Spark desktops people already own more useful for local AI work. The release also fits Nvidia's broader support for open local AI, including the July letter it signed with 34 other companies urging Washington not to restrict open-weight AI. The Apple M4 support cuts the other way, since a tool that will hand work to a Mac isn't a closed Nvidia ecosystem.
