惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

人人都是产品经理
人人都是产品经理
Apple Machine Learning Research
Apple Machine Learning Research
云风的 BLOG
云风的 BLOG
罗磊的独立博客
博客园 - 三生石上(FineUI控件)
量子位
GbyAI
GbyAI
腾讯CDC
T
Tailwind CSS Blog
博客园 - Franky
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
D
Docker
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏
The GitHub Blog
The GitHub Blog
Microsoft Security Blog
Microsoft Security Blog
Stack Overflow Blog
Stack Overflow Blog
Hugging Face - Blog
Hugging Face - Blog
小众软件
小众软件
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
N
Netflix TechBlog - Medium
Jina AI
Jina AI
IT之家
IT之家
Y
Y Combinator Blog

The Register

Grafana offers AI assistant for free, warns users not to go mad Right to repair champ Framework punts modular 13in laptop with Core Ultra Series 3 Scotland Yard can keep using live facial recognition on Londoners, say judges UK tribunal sends £2B claim accusing Microsoft of overcharging for licensing to trial Nation-states want to cause harm, not just steal cash - stop handing your cyber defenses to the cheapest contractor Murder, she wrote: Ex-FBI chief wants some ransomware crims charged with homicide Phone-to-satellite use goes into orbit, growing 25% in 8 months macOS ClickFix attacks deliver AppleScript stealers to snarf credentials, wallets Anthropic bakes memory fixes into Bun 1.1.13 as developers complain of leaks The spaghettified DBMS chart that shows Oracle's crown is slowly slipping Yet another ex-ransomware negotiator admits turning rogue after payoff from crimelords FAA grounds Blue Origin's New Glenn as it probes missed satellite delivery 'mishap' AMD's Ryzen 9 9950X3D2 Dual Edition tested: Gratuitous overkill with a price to match AI-assisted intruders pwned Vercel via OAuth abuse and a pilfered employee account Crook claims to leak 'video surveillance footage' of companies Met police trials snoop tech platform in push to cuff more London shoplifters England's school phone ban gets teeth, just in time to bite no one Adaptavist Group breach spawns imposter emails as ransomware crew claims mega-haul Panasonic creates device-locked QR codes to speed facial biometric capture Iran claims US used backdoors to knock out networking equipment during war NASA Inspector fears new spacesuits won’t be ready for Moon landing Vibe coding upstart Lovable denies data leak, cites 'intentional behavior,' then throws HackerOne under the bus Trump-branded datacenter project fails to make itself great, again World's blandest man steps down from CEO job to spend more time in tastefully appointed home Chase got a spiff of $77 million to create one job with New York datacenter Scot becomes second Scattered Spider-linked crook to plead guilty in US You too can build a nuclear battery from junk you have lying around the house Schmoozebots: study finds flattery will get AI everywhere One of Europe's sovereign cloud picks may not be so-sovereign after all New Android development tool designed for robots, not humans
Nvidia's Grace Blackwell superchips are officially coming...
Tobias Mann · 2026-06-01 · via The Register

Systems

Forget Wintel, we're living in a Winvidia world now

COMPUTEX 2026 It only took a year and a half but the same silicon at the heart of Nvidia's DGX Spark AI workstations will soon be powering Windows PCs.

During his GTC Taiwan keynote on Monday, Nvidia CEO Jensen Huang revealed the N1X, a high-end mobile processor that combines an Arm-based CPU co-designed with MediaTek with a Blackwell based GPU on board.

Marketed under the “RTX Spark” banner, Nvidia’s new notebooks and mini PCs signal a deeper push into the a PC arena long dominated by Intel and AMD. But while the PCs are new, the chip powering them isn’t.

Nvidia was rumored to be working on the N1X for several years now. At CES in 2025 the GPU slinger fanned the rumor mill flames when it unveiled the DGX Spark — then codenamed Project Digits

The $4,000 AI workstation was powered by a miniaturized Grace Blackwell processor packing 20 ARMv9 CPU cores and a Blackwell GPU with 6,144 CUDA cores, capable of up to 500 teraFLOPS of FP4 compute  — or 1 petaFLOP if you happen to have a workload that supports sparsity. That’s fed by 128 GB of unified memory.

Rendered view of the RTX Spark

If that sounds familiar, that’s because the N1X and GB10 are essentially the same chip. The liberal use of the term “up to” in Nvidia’s marketing does, however, suggest that not all SKUs will have all CPU or GPU cores enabled.

The silicon may be the same but the operating system isn’t. While Nvidia’s DGX Spark and GB10 partner systems shipped with DGX OS, a lightly customized version of Ubuntu 24.04, RTX Spark systems will ship with Windows.

This opens the door to high performance mobile gaming using integrated Nvidia graphics. The GPU giant claims the N1X-based systems should be able to manage 100 frames per second at 1440P in AAA games, presumably with the help of AI upscaling tech like DLSS.

With up to 128 GB of unified memory shared between the CPU and GPU, RTX Spark systems should be able to handle creative workloads previously limited to high-end workstations.

Nvidia suggests top end RTX Spark systems should be able to handle 3D renders requiring 90-plus gigabytes of memory, edit 12K video, generate AI videos, and run 120 billion parameter LLMs with the large context windows required for local agents.

As part of the announcement, Huang teased an appearance alongside Microsoft CEO Satya Nadella to discuss the future of AI PCs during the software titan’s Build conference, which kicks off tomorrow.

As for the hardware, Nvidia has clearly set a high bar for quality. In addition to DGX Spark-style Mini PCs, RTX Spark systems will range from 14 to 16-inches in size, feature aluminum chassis, and color accurate OLED displays with Nvidia G-Sync.

The first N1X-based PCs and notebooks from the likes of Asus, Dell, HP, Lenovo, Microsoft and MSI are expected to begin rolling out this fall. 

We’ve asked Nvidia to confirm RTX Spark systems pricing, but don’t expect the top end variants to be cheap. GB10-based systems ranged from $3,000 to $4,000 at launch. Memory prices have only gone up since then with the DGX Spark now retailing for $4,699. ®