← Back
VentureBeat AI

Perplexity partners with Nvidia to launch Portable Computer, a fully local AI agent with zero token costs

•11 min read•
#agents#deployment#nvidia
Perplexity partners with Nvidia to launch Portable Computer, a fully local AI agent with zero token costs
Level:Advanced
For:AI Engineers
✦TL;DR

Perplexity’s new Portable Computer lets its “Computer” agent run entirely on‑premise using Nvidia hardware—specifically Nvidia DGX Spark desktops or Linux machines equipped with Nvidia RTX GPUs—by loading a 27‑billion‑parameter Qwen model locally. The full agent stack (model, harness, inference engine, tools, and security sandbox) is bundled into a single app, eliminating cloud token costs and keeping data on the device. Engineers can now prototype multi‑step AI workflows (e.g., document review) without provisioning separate inference servers or incurring usage fees.

⚡ Key Takeaways

  • 27‑billion‑parameter Qwen model runs at full GPU utilization on a DGX Spark.
  • Portable Computer bundles the agent harness, inference engine, tools, and sandbox into one installable app.
  • Zero cloud billing credits are consumed; all work stays local unless the user explicitly permits a cloud step.
  • The app targets Nvidia RTX‑GPU‑enabled Linux machines as well as DGX Spark desktops.
  • If a task requires a more powerful frontier model, the system will request permission before sending that step to the cloud.
💡 Why It Matters

Shipping a complete, locally‑executed AI agent removes data‑privacy concerns and eliminates per‑token costs, enabling production teams to run sophisticated multi‑step workflows on existing Nvidia hardware without building a custom stack.

✅ Practical Steps

  1. Install Portable Computer on a DGX Spark or a Linux machine with Nvidia RTX GPUs to run the bundled local AI agent stack.

Want the full story? Read the original article.

Read on VentureBeat AI ↗

More like this

Introducing workload recovery and expanded infrastructure checks on Amazon SageMaker HyperPod

AWS ML Blog•#deployment

Introducing Unity Gateway Insights

Databricks Blog•#deployment

Introducing Gemini 4 Neon

Google DeepMind•#llm

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Hugging Face Blog•#llm

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING