# DGX Spark Live: Perplexity Portable Computer Goes Local

## Executive summary

Perplexity introduced Portable Computer, an agent platform designed to run fully on-device using NVIDIA DGX Spark. This system brings complex, multi-step AI workflows—including inference and agent harnessing—to a simple local interface, prioritizing data privacy by keeping sensitive processing offline. While defaulting to local models (like Qwen 27B), the architecture supports controlled escalation to frontier cloud models only when necessary or permitted.

## Key takeaways

- Local-First AI Architecture: Portable Computer runs the entire stack—including agent harness and inference—locally on DGX Spark, eliminating token caps and metered compute for local tasks. This ensures sensitive data (e.g., tax documents) remains fully private [0:03:42].
- Simplified Agent Experience: The platform abstracts away the underlying complexity of agent harnesses and inference, providing users with a simple interface to execute sophisticated AI tasks without needing deep knowledge of the stack [0:01:58].
- Hybrid Scalability: While designed for local operation, Portable Computer is 'local first' but can escalate to use frontier cloud models (e.g., Anthropic, OpenAI) and connect via a robust connector ecosystem when required [0:02:37].

## Technical details

- Hardware & Compatibility: The initial launch targets the NVIDIA DGX Spark. However, Perplexity is working to expand compatibility, expecting support for RTX devices with at least 24 GB of VRAM [0:03:58].
- Model Stack and Performance: The system utilizes post-trained models like the Perplexity 27 billion parameter Qwen model (for initial demos) and Nemotron 3.5 Lightning. The architecture is designed to manage inference locally while maintaining frontier-level utility [0:01:48, 0:03:16].
- Agent Workflow Management: The system features a built-in mechanism for controlled cloud escalation, requiring user approval before sending traffic to external/frontier models. It also includes advanced sandboxing for safe execution [0:02:45].

## Practical implications

- For build engineers, this represents a shift toward edge/local AI deployment models, significantly reducing reliance on constant cloud connectivity for core business logic.
- The emphasis on local processing solves major enterprise data privacy and compliance challenges (e.g., handling tax or financial records).
- The modular design—separating the agent harness from inference and allowing pluggable models—offers flexibility for custom enterprise integration.

## Topics

Agentic AI, Local Compute, Data Privacy, NVIDIA DGX Spark, AI Infrastructure, DGX Spark, Perplexity Pro/Max Subscription, NVIDIA Developer Website

Source: https://www.youtube.com/watch?v=euQoPqGXVlk