NVIDIA PAIR (Personal AI Router)
NVIDIA's free, open-source personal AI router that spreads local model workloads across PCs on your network; out of beta Oct 13, 2026.
Overview
NVIDIA PAIR is a free, open-source personal AI router that moved out of beta on October 13, 2026. It discovers compatible PCs on a local network and distributes AI workloads across them, and the Oct 2026 update adds llama.cpp support, direct Hugging Face model downloads, and RTX Spark support. It runs on Windows, Linux, and macOS, and its source is on GitHub at NVIDIA/Personal-AI-Router.
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- Discovers compatible PCs on the local network and splits AI workloads across them
- llama.cpp support added in the Oct 2026 update
- Direct Hugging Face model downloads
- RTX Spark support
- Runs on Windows, Linux, and macOS
- Open source on GitHub (NVIDIA/Personal-AI-Router)
Use cases
- Pooling several home or office PCs to run a larger local model
- Hybrid local/cloud routing for agent apps
- Offloading agent inference from a thin laptop to a stronger desktop
Pricing
Free and open source.
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- 13 Oct 2026
- Record updated
- 16 Oct 2026
- Record last checked
- 16 Oct 2026