Nvidia · Intel · AI Inference · Decrypt
Nvidia launched RTX Spark at the same Computex where Perplexity made its announcement
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
Perplexity's differentiation is the orchestration layer.
Key facts
- Perplexity's revenue grew from $100 million to $500 million while headcount increased 34%, Srinivas announced in April
- Perplexity CEO Aravind Srinivas took the stage at Computex 2026 in Taipei on June 2 alongside Intel CEO Lip-Bu Tan to announce what the company calls the first hybrid local-server inference
- Microsoft's Foundry Local reached general availability in April 2026, enabling full AI inference on Windows, macOS, and Linux without cloud dependency
- Srinivas said the approach is "chip agnostic"—the Computex demo ran on Intel Core Ultra Series 3, but Nvidia processors are also supported
Summary
Perplexity announced "hybrid agentic inference" at Computex 2026, a system that automatically splits AI workloads between a user's local device and cloud-based frontier models—no manual configuration required. The feature is coming to Perplexity Computer in July, demoed on Intel Core Ultra Series 3 processors and currently exclusive to the Windows PC app. CEO Aravind Srinivas framed the move around cost efficiency: Perplexity's revenue grew fivefold to $500 million while headcount rose 34%, and offloading inference to user hardware keeps that ratio working. Perplexity CEO Aravind Srinivas took the stage at Computex 2026 in Taipei on June 2 alongside Intel CEO Lip-Bu Tan to announce what the company calls the first hybrid local-server inference orchestrator. “Today we're announcing the next step for Personal Computer: the first hybrid local-server inference orchestrator,” Perplexity announced.