NVIDIA launches PAIR beta to turn your RTX PCs, DGX Spark and Macs into one local AI inference cluster
BenBajarin · x · 2026-09-04
NVIDIA released the Personal AI Router (PAIR) beta, which links machines on your home network into a single local inference cluster:
- Personal AI cluster: auto-discovers RTX Windows machines, DGX Spark, and Macs (M4+) and runs them as one cluster—no cables or rack setup
- Agent workload routing: intelligently proxies inference requests to idle local nodes across operating systems
- Ollama & LM Studio support: exposes one consistent local endpoint for existing tools
- Privacy-first: prompts, files, and agent context stay on your network
Supports Windows 11, DGX OS, Ubuntu, and macOS Tahoe; any GeForce RTX 20-series or newer GPU qualifies. Free beta download.
Related event: NVIDIA Launches PAIR to Turn Home Devices into a Local AI Cluster(4 posts)→
More from coding & agent
- Claude Code self-hosted environments enter public beta — EricBuess · 2026-09-04
- Compared 6 AI Visibility Tools: $199 Ahrefs Actually Costs $974/Mo at Scale — Informal-Dust4499 · 2026-09-04
- AI agent River cleared 70% of vuln backlog in 11 days, merge rate 10% to 80% — jevon · 2026-09-04
- Databricks found $1.2M/year in wasted AI spend from 7 MCP-server bugs — matei_zaharia · 2026-09-04
- Open-sourced: training code for a mobile screenshot classifier (feeds, gallery, chats) — TheMoonMidas · 2026-09-04
- Model routing cuts LLM errors 46% at same cost, Martian study finds — SucceededMind · 2026-09-04