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

奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
WordPress大学
WordPress大学
N
Netflix TechBlog - Medium
T
Troy Hunt's Blog
Help Net Security
Help Net Security
L
LINUX DO - 最新话题
aimingoo的专栏
aimingoo的专栏
Microsoft Azure Blog
Microsoft Azure Blog
Y
Y Combinator Blog
Attack and Defense Labs
Attack and Defense Labs
M
MIT News - Artificial intelligence
Security Archives - TechRepublic
Security Archives - TechRepublic
SecWiki News
SecWiki News
博客园 - 三生石上(FineUI控件)
P
Privacy International News Feed
AI
AI
PCI Perspectives
PCI Perspectives
L
Lohrmann on Cybersecurity
G
Google Developers Blog
N
News | PayPal Newsroom
Hugging Face - Blog
Hugging Face - Blog
B
Blog RSS Feed
The Hacker News
The Hacker News
Apple Machine Learning Research
Apple Machine Learning Research
B
Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
I
InfoQ
Webroot Blog
Webroot Blog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
V
Visual Studio Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
U
Unit 42
A
About on SuperTechFans
Cyberwarzone
Cyberwarzone
Schneier on Security
Schneier on Security
Cisco Talos Blog
Cisco Talos Blog
D
Docker
博客园_首页
The Cloudflare Blog
S
Secure Thoughts
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
The Last Watchdog
The Last Watchdog
大猫的无限游戏
大猫的无限游戏
S
SegmentFault 最新的问题
Last Week in AI
Last Week in AI
F
Fortinet All Blogs
I
Intezer
Google DeepMind News
Google DeepMind News
Know Your Adversary
Know Your Adversary
Simon Willison's Weblog
Simon Willison's Weblog

NVIDIA Archives - VICE

Red Dead Redemption 2 Developer Warns Nvidia DLSS 5 Is “Scary” The Best Options for Cloud Gaming in 2026 New Report Suggests Phased Price Hikes for AMD and Nvidia GPUs in 2026 Nvidia Removing Unlimited Game Streaming for All Users In a Few Days Borderlands 4 Gets Disappointing Performance Update Before Launch Nvidia’s New GeForce RTX 5060 GPU Sucks, Apparently Nvidia Announces Release Dates for RTX 5070—and Really, It Could Be Worse NVIDIA Says It'll Run Out of RTX 5090 and 5080, Internet Loses Its Shit NVIDIA Shoots for the Stars With Cosmos, an Open-Source Platform to Make AI for Robots
NVIDIA Just Unveiled a Personal Supercomputer That’s a Jump to Light Speed for AI Users
Matt Jancer · 2025-01-08 · via NVIDIA Archives - VICE

Hoo, boy. NVIDIA might’ve stolen the show at CES before it even began. The world’s largest annual consumer tech show, held in Las Vegas every January, didn’t entirely start until today, but NVIDIA announced late last night at 6:30 PM PST that starting in May, it’ll sell you a “desktop supercomputer” about the size of a Mac mini for about the price of a mid-range television and home audio setup. Huh??

How can something so tiny contain so much (super)computing power? Is it, like all computers, full of magic? Don’t be a silly goose. Of course it is. What we want to know is whether it’s full of black magic or the regular kind. Or maybe that old-timey kind with a “k,” magick.

Videos by VICE

how pow, powerful

“With Project DIGITS, the Grace Blackwell Superchip comes to millions of developers,” Jensen Huang, founder and CEO of NVIDIA, said during the unveiling. “Placing an AI supercomputer on the desks of every data scientist, AI researcher and student empowers them to engage and shape the age of AI.”

Headlines the morning after the announcement are echoing and blaring that Digits is “1,000 times as powerful as a laptop.” It didn’t just raise my eyebrows. It made them fly off into the atmosphere, where they’re now hanging in a low-pressure system over the Bronx.

NVIDIA DIGITS Pre-Launch Image – Credit NVIDIA

For the low, low price of $3,000—less than the cost of a MacBook Pro M4 Max—you can buy a personal, desktop supercomputer the size of a box turtle that has more power than Beyonce and the Space Shuttle put together?

FLOPping around from excitement

Notably NVIDIA’s press announcement doesn’t make the claim that it’s 1,000 times more powerful than a laptop, and it’s not on their webpage for DIGITS. So where did it come from?

NVIDIA says DIGITS provides one petaFLOPS of “AI computing performance.” And because I feel the grammar police lining up a blowdart aimed at me, the “ps” in “petaFLOPS” stands for “per second,” so the “s” says even when it’s a singular noun.

Live Science did some math when it reported its story on DIGITS, and referencing this IBM post on measuring supercomputer power, they concluded that since the most powerful supercomputers in the world have a processing of about 1,000 petaFLOPS—which is a million times more powerful than a laptop, according to IBM—that with one petaFLOPS of power, DIGITS would be 1,000 times as powerful as a laptop.

Broadly speaking, though, how powerful a computer is depends on which task you’re referring to. It may be 1,000 times as powerful as a (typical? High-end?) laptop at wielding AI, but not 1,000 times as powerful for, say, editing videos. So DIGITS could end up as the hardware version of the killer app for AI development and use, but not the be-all-end-all for the masses who simply want a kick-ass, powerful computer for home use. We’ll have to dig more into its specifications and details as they become available closer to its launch.

Want to know what it looks like? Us too. NVIDIA shared a couple of images during the launch, but the design doesn’t seem to be finalized. What we see now might not match what we see when it’s released this May. You can register to be notified when it becomes available for sale or pre-sale.

NVIDIA’s on track to become the most valuable company in the world (again), after approving investors rallied its stock the morning after NVIDIA’s announcement. As for us, healthy skepticism means we’ll want to delve into DIGITS as more information becomes available. Stay tuned.