Perplexity and Nvidia Launch Fully Local AI Agent With Zero Token Costs

Perplexity and Nvidia have jointly unveiled Portable Computer, a local-first iteration of Perplexity's AI agent platform that operates AI models, files, tools, and workflows directly on Nvidia-powered Linux hardware. This innovative approach ensures that local tasks incur no token costs and keeps data on-device by default. Users are only prompted for permission when the system needs to escalate a step to a cloud model.

Nvidia, which has been promoting AI data centers worth a trillion dollars over the past two years, views this local AI development as both a significant milestone and a strategic opportunity. Nader, Nvidia's director of developer technology, emphasized that local AI has transitioned from being merely a hobbyist curiosity to a practical tool.

Previously, running quantized models on low-resource devices was intriguing but not highly practical. However, the emergence of more useful open-source models has changed the landscape. Portable Computer is now available for Pro, Max, Enterprise Pro, and Enterprise Max subscribers on Linux, with Windows support scheduled for September. To ensure a great user experience, Nvidia recommends using an RTX GPU with at least 24GB of VRAM, a threshold deemed sufficient for a smooth and broadly available performance.