I tried local AI on HP’s Omnibook Ultra – it’s a private, powerful beast with zero token fees - ZDNET
By Google News Technology ·
Back at the dawn of the PC era, PC Magazine’s legendary editor, Bill Machrone, came up with Machrone’s Law: “The machine you want will always cost about $5,000.” Maybe that number is a little higher today thanks to the current RAM crisis, but adjusted for inflation, Machrone’s Law still holds true. The proof? I have a $7,000 notebook PC sitting on my desk right now, and I must confess that I really, really want it.
Also: I put Lenovo’s RTX Spark laptop through a completely bonkers AI coding test – and it passed
The HP OmniBook Ultra is an absolute beast. It’s powered by Nvidia’s RTX Spark, with 128 GB of unified memory, 2 TB of fast Gen5 NVMe storage, and a great-looking 16-inch OLED display. It weighs nearly five pounds, but it isn’t really so much a portable PC as it is a personal data center, offering 1 petaflop of FP4 AI performance.
I am not the target market for this PC. But after using it for a few weeks, I am seriously tempted. For AI-related work, its GPU has many times the power of a garden-variety Copilot+ PC, and it’s able to take full advantage of the unified memory.
This PC finally gave me a chance to tackle a project I’ve had on my to-do list for years: creating a fully searchable index of 20 years’ worth of my posts here at ZDNET. With the help of a powerful local AI model, this PC got the job done in one day, without costing me a dime in AI subscription charges or sending my data to someone else’s cloud.
One reason my project completed so quickly was that I was able to run it uninterrupted. I used Copilot to help me set up the working environment initially, using the open-source llama.cpp inference runtime, the open-weights Qwen3.8-27B large language model, and a coding harness called Cline, running as an extension in Visual Studio Code. With a…
Originally published by Google News Technology
