Nvidia Unveils Project DIGITS: A Personal AI Supercomputer for $3,000

Nvidia drops new personal AI supercomputer -- DIGITS costs $3,000 and is out in May

I write about AI for a living and can't wait to try this new Nvidia Digits personal supercomputer Nvidia is releasing a new type of AI PC. Unlike the offerings from Microsoft and others, this will be a mini supercomputer in your home able to run even the more advanced AI models offline. Announced at CES 2025, Project DIGITS uses the new Nvidia GB 10 Grace Blackwell Superchip with a supercomputer level petaflop of AI computing. It comes with a hefty price tag, starting at $3,000, but Project DIGITS will allow users to run models with up to 200 billion parameters. This means models previously requiring expensive cloud infrastructure can run on your desktop. The main market for the device will be developers wanting to test new AI applications, but it could also be used to generate AI video and image content. Project DIGITS main purpose seems to be as a desktop showcase for the GB10 AI superchip. Each machine will includje 128GB of unified, coherent memory and 4TB of storage. Users can even link two together to run 405 billion parameter models, previously only the reserve of the big AI labs. Having a machine that costs about the same as one of the best gaming laptops with the power of a supercomputer is a huge leap for AI development. It will allow companies and researchers to quickly prototype, fine-tune and test models locally before deploying them to the cloud. "AI will be mainstream in every application for every industry. With Project Digits, the Grace Blackwell Superchip comes to millions of developers," Nvidia CEO Jensen Huang explained. Huang added: "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." This isn't the first AI computer built by Nvidia specifically for developers. For example, it launched the $249 Jetson in December for AI hobbyists and start-ups that can handle 8 billion parameter modes. The push to create developer-friendly hardware comes as Nvidia is facing increasing competition from other platforms and chip-makers trying to convince developers to move away from the CUDA framework.

Can Nvidia Project Digits democratize AI for millions more people?

A personal AI supercomputer in the hands of more people could make AI more equitable. The last 12 months have seen a lot of attention brought to the term "AI PC," used to denote computers housing processors or APUs with powerful NPUs (neural processing units) for enhanced AI computation. However, even then, these machines lack the raw performance that many more powerful AI applications require to tackle complex generative AI tasks, leaving a lot of the work to be done in the cloud. Until Nvidia announced Project Digits, that is. A personal AI supercomputer, and our Laptop Laurel winner for the best use of AI at CES 2025. While the Nvidia RTX 50 series GPUs dominated the conversation at CES 2025, the company's Project Digits was a massive announcement that went a bit under the radar. Nvidia calls it an "AI Supercomputer on your desk," delivering a petaflop of AI performance in a form factor that appears similar to a Mac Studio. Who needs that kind of AI power? It's targeted at AI researchers, data scientists, and the education market to help run large AI models without relying on ChatGPT or another cloud-based solution. The key to its performance is the GB10 Grace Blackwell Superchip, designed in partnership with MediaTek. It also boasts 128GB of RAM and up to a 4TB NVMe SSD. Running Nvidia's Linux-based DGX OS, it will be capable of running 200-billion-parameter large language models or 405-billion-parameter models if pairing two Digits together. While it feels like AI is everywhere in the tech world already, this kind of (relatively) affordable system can put it in the hands of far more users, which is an AI advancement I can get behind. Starting at $3,000, it isn't cheap, but assembling a comparable AI computer could run over $10,000 in the not-so-distant past. Project Digits is coming in May from Nvidia and its partners.

Nvidia's Project Digits desktop AI supercomputer fits in the palm of your hand -- $3,000 to bring 1 PFLOPS of performance home

Nvidia announced many new innovations in its 90 minute long CES keynote/victory lap, but the intriguing closer was its Project Digits AI supercomputer. Arriving in May, Project Digits (name apparently subject to change) will bring 1 PFLOPS of FP4 floating point performance in a form factor which fits snugly in the hands of Nvidia boss Jensen Huang. Project Digits was conceptualized with the same concept as Nvidia's DGX 100 servers; to bring a ready-made AI supercomputer solution to end users without the infrastructural concerns of a full supercluster solution. Where DGX 100 fits in server racks, Project Digits fits on the desktop with a similar footprint to a Mac Mini. Digits is powered by the GB10 Grace Blackwell Superchip, a collaboration between Nvidia and MediaTek. Nvidia's Blackwell GPU, offering the touted 1 petaFLOP of performance, sits on a die with a 20-core Grace CPU thanks to NVLink C2C. The superchip is joined on the board by 128GB of LPDDR5X memory from Micron and a 4TB NVMe SSD. An Nvidia ConnectX smart network adapter also sits in the computer, providing NCCL, RDMA, and GPUDirect support. Arm and Nvidia both seem excited about the Grace Blackwell collaboration. "The NVIDIA Grace CPU features our leading-edge, highest performance Arm Cortex-X and Cortex-A technology, with 10 Arm Cortex-X925 and 10 Cortex-A725 CPU cores," shared Arm in its own press release. "Our collaboration with Arm on the GB10 Superchip will fuel the next generation of innovation in AI," adds Ashish Karandikar, Nvidia's VP of SoC Products. This extreme power packed into a tiny footprint means that a single Project Digits unit can run up to 200-billion-iteration AI large language models. For context, OpenAI's GPT-4o model is a 12-billion-iteration model, meaning Project Digits could run and configure ChatGPT locally. When paired with another unit, in "double Digits", the support increases to 405B models. End users looking for local access to a larger AI computing solution will be the target audience for Project Digits. The high-power machine is tuned for AI, on the hardware and software ends. Project Digits comes with Nvidia's full AI Enterprise software stack pre-installed; libraries, frameworks, and infrastructure management tools to connect with and manage a more expansive AI solution. Digits can serve as a box to communicate with a cloud solution via one's PC, or can be used as a Linux workstation on Nvidia's DGX OS distro. Users "can prototype, fine-tune, and test models on local Project DIGITS systems," then deploy them on the cloud or local data center infrastructure, says Nvidia's accompanying press release. Enterprises or researchers/students are set to be the target audience per Nvidia's literature, though the truly devoted hobbyist will likely not be stopped from buying the machine. "AI will be mainstream in every application for every industry," said Huang. "With Project Digits, the Grace Blackwell Superchip comes to millions of developers. 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." AI was the major focus of Nvidia's CES keynote this year, focusing largely on its most valuable contributions beyond chatbots and image generation. Those interested in Project Digits need only wait until May, when Digits releases starting at $3,000. From where we sit, Project Digits is a shockingly impressive piece of hardware for its size and continues carrying DGX 100's banner of democratizing AI training. For our recap of the rest of Nvidia's CES keynote, including the $549 RTX 5070, click right here.

Nvidia's $3,000 Project Digits puts a 1-Petaflop AI on your desk

During a 90-odd-minute keynote address at CES 2025 in Las Vegas on Monday, Nvidia CEO Jensen Huang showed off a powerful desktop computer for home AI enthusiasts. Currently going by Project Digits, this $3,000 device takes up about as much space as a Mac mini and offers 1 PFLOPS of FP4 floating point performance. Nvidia reportedly used its DGX 100 server design as inspiration for the self-contained desktop AI, with Projects Digits being powered by a 20-core GB10 Grace Blackwell Superchip on 128GB of LPDDR5X memory with a 4TB NVMe solid-state drive (SSD). Recommended Videos "AI will be mainstream in every application for every industry," Huang said during the keynote. "With Project Digits, the Grace Blackwell Superchip comes to millions of developers. 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." Nvidia collaborated extensively with Arm to create the Grace Blackwell chip. "Our collaboration with Arm on the GB10 Superchip will fuel the next generation of innovation in AI," Ashish Karandikar, Nvidia's vice president of SoC Products, said in the company's press release. Get your weekly teardown of the tech behind PC gaming ReSpec Subscribe Check your inbox! Privacy Policy That much compute power means a Project Digits device will be able to locally run a 200-billion-iteration AI large language model (LLM) when it is scheduled for release in May. ChatGPT using the GPT-4o model, for example, is only 12-billion iterations. Digits devices can also be tethered together, increasing their theoretical max model size up to 405 billion iterations. The company is targeting users who need full-power LLMs running locally as their primary customers for Project Digits. As such, each device comes preloaded with Nvidia's entire AI Enterprise software stack -- everything an enterprise and research outfit would need to get their AI up and running -- with the idea being that users "prototype, fine-tune, and test models on local Project Digits systems" before deploying them to the cloud. Artificial intelligence has long been criticized as a top-down technology in that its development has largely been directed by a select number of companies and institutions (specifically, those wealthy enough to afford the massive training and operating costs AI requires). This is the precise opposite of how the first computer revolution came about in the 1970s to 1990s, where uncountable legions of individual hobbyists, tinkerers, and experimentalists drove the development of personal computer technology. Project Digits could provide the same opportunity for the AI industry. Granted, $3,000 will surely limit its initial adoption to a degree, but to be fair, people didn't blink at the $3,500 price tag on Apple's failed Vision Pro headset, and that thing was just a fancy display strapped to their face. If you're interested in trying Digits for yourself, Nvidia has a notification sign-up on its website.

Nvidia debuts Project DIGITS, a palm-sized AI supercomputer that can sit on any desk - SiliconANGLE

Nvidia debuts Project DIGITS, a palm-sized AI supercomputer that can sit on any desk Nvidia Corp. is making its most powerful graphics processing units accessible to anyone with the coming launch of Project DIGITS - a "personal AI supercomputer" that's powered by the soon-to-launch Nvidia GB10 Grace Blackwell Superchip. The AI supercomputer was announced late today at the CES consumer electronics show in Las Vegas. When it launches in May, Project DIGITS will provide users with access to 1 petaflop of artificial intelligence computing performance, giving researchers, data scientists and students the kind of performance normally limited to big enterprises, right there on their desks. It will support the prototyping, training and fine-tuning of advanced large language models, as well as inference, making it possible for anyone to develop artificial intelligence systems that can match the power of applications like ChatGPT. Nvidia's upcoming GB10 Superchip is a system-on-a-chip that's powered by its most advanced GPU, the Nvidia Grace Blackwell. It has all of the supporting components required to run large-scale AI projects, with dozens of CUDA cores and fifth-generation Tensor Cores connected to equally high-performance Nvidia Grace central processing units by the company's chip-to-chip interconnect technology, NVLink. According to Nvidia, the GB10 Superchip enables the Project DIGITS supercomputers to deliver immense AI computing resources to anyone via a standard laptop or PC. Each machine will provide access to 128 gigabytes of unified, coherent memory and up to 4 terabytes of NVMe storage. That's more than enough to run a 200 billion-parameter LLM, meaning users will be able to build and experiment with LLMs that exceed the capabilities of OpenAI's GPT-3 model, which has 175 billion parameters. For those who need even more power, it will be possible to link two Project DIGITS AI supercomputers together using Nvidia's ConnectX networking technology, to support models with up to 405 billion parameters, the company said. Nvidia co-founder and Chief Executive Jensen Huang (pictured, with Superchip) said during a CES keynote that Project DIGITS is all about making the tools for advanced AI development more accessible, so that everyone can participate in building the future. He explained that the aim is to provide affordable access to the Grace Blackwell Superchip for millions of developers. There may still be millions of developers left behind though, for the Project DIGITS machines can't really be described as "cheap," with prices starting at $3,000. But Huang seems to think there will be many AI developers who are willing to pay that kind of money. "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," Huang said. Those developers will be able to create, fine-tune and test their models on Project DIGITS before deploying them on the Nvidia DGX Cloud platform, accelerated cloud instances or their own on-premises data center infrastructure, the company said. To aid developers using Project DIGITS, the company is also providing them with access to an extensive library of AI development tools, including software development kits, frameworks and prebuilt AI Models, all of which can be found within the Nvidia NGC Catalog on the Nvidia Developer portal.

Nvidia's Digits is a tiny AI supercomputer for your desk

With all eyes on Nvidia's new graphics cards (and for good reason - these things are pretty powerful), the company released something that may end up being even bigger news: A personal AI supercomputer called Project Digits (we'll just call it Digits from now on because that's way cooler). Digits is a tiny, Mac mini-like personal computer that should fit on pretty much every desk. You connect it to a keyboard and a monitor, plug it into power, and you're good to go. But what's inside makes it pretty special. Digits is powered by Nvidia's new GB10 Grace Blackwell Superchip, which delivers up to 1 petaflop of AI performance, and Nvidia teamed up with MediaTek to make the chip more energy-efficient, meaning that running it requires the kind of power you get from a standard power outlet. The GB10 is paired with 128GB of RAM and up to 4TB of NVMe storage. All of this will enable developers to run up to 200-billion-parameter large language models (LLMs). Using Nvidia ConnectX tech, they'll also be able to to pair two Digits computers to run up to 405-billion-parameter models. Most of this stuff probably makes little sense to folks who aren't in the AI app development business. But for example, ChatGPT 3.5 had 175 billion parameters (ChatGPT 4 is much larger but we don't know the exact numbers), while Meta's most powerful LLM, Llama 3, has 405 billion parameters). This means you can run a very, very powerful LLM at home instead of relying on cloud infrastructure. "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," Jensen Huang, founder and CEO of Nvidia, said in a written statement. Developers who use Digits will be able to access Nvidia's library of AI software including development kits, orchestration tools, frameworks and models available in the Nvidia NGC catalog and on the Nviia Developer portal. They'll also have access to the Nvidia NeMo framework, and Nvidia RAPIDS libraries. The biggest news here, perhaps, is the price. Digits will be available in May, starting at $3,000. This sort of money should make it available to a large number of smaller companies and researchers, who will use it to create and test AI apps. If this still sounds too expensive, you can try Nvidia's Jetson. It's a $249 AI home computer that launched last December, and it can handle up to 8 billion parameters.

NVIDIA's Announces $3000 Supercomputer

It's called 'Project DIGITS' and can run powerful AI models locally. Leading chipmaker NVIDIA unveiled Project DIGITS, a new small supercomputer, at the Consumer Electronics Show (CES) 2025. It is aimed at AI researchers, data scientists, and students across the world. The supercomputer provides access to the GB10 Grace Blackwell Superchip, which Jensen Huang, CEO of NVIDIA, calls a 'super secret chip'. The GB10 features a 20-core NVIDIA Blackwell GPU, one of the most powerful AI hardware systems available today. The CPU was built in collaboration with MediaTek. Project DIGITS features 128 GB of unified memory and offers storage options of up to 4TB. Similar to a typical computer, DIGITS requires only a standard electrical outlet to operate. It operates on a Linux-based NVIDIA DGX operating system. The supercomputer can also run up to 200 billion parameter LLMs locally, and if you have two of them, NVIDIA says you can link them up to run AI models double the size. Project DIGITS allows users to deploy AI models on the NVIDIA DGX cloud and leverage all the tools present inside NVIDIA's AI Enterprise software platform. For instance, you can fine-tune models on the NeMo framework and build agents on NVIDIA Blueprints and NIM microservices. The higher performance and portability increase the cost. Project DIGTIS will be available in May of this year and will cost a whopping $3000. "AI will be mainstream in every application for every industry. With Project DIGITS, the Grace Blackwell Superchip comes to millions of developers," said Jensen Huang, founder and CEO of NVIDIA. "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," he added. At first glance, there's no doubt that Project DIGITS is entering the Mac Mini territory, at least in terms of the form factor. "I must have the Nvidia Project Digits for my home lab. 128GB pooled RAM, 4TB storage, the size of a Mac mini, Running DGX OS, a Linux-based OS. The coming years are going to be wild in the world of AI and robotics," said Jamie Madden, a machine learning developer on X. In December of last year, NVIDIA introduced the Jetson Orin Nano Super Developer Kit, a compact generative AI supercomputer now priced at $249, down from $499. According to the company, it offers enhanced performance with 67 INT8 TOPS, marking a 70% improvement over its predecessor, alongside a memory bandwidth of 102GB/s, which is a 50% increase.

Nvidia's $3,000 'Personal AI Supercomputer' Will Let You Ditch the Data Center

Nvidia CEO Jensen Huang also announced new AI models for robots, self-driving cars, and autonomous agents during a keynote address at CES. Nvidia already sells boatloads of computer chips to every major company building proprietary artificial intelligence models. But now, at a moment when public interest in open source and do-it-yourself AI is soaring, the company announced it will also begin offering a "personal AI supercomputer," that starts at $3,000 later this year that anyone can use in their own home or office. Nvidia's new desktop machine, dubbed Digits, will go on sale in May and is about the size of a small book. It contains an Nvidia "superchip" called GB10 Grace Blackwell optimized to accelerate the computations needed to train and run AI models, and comes equipped with 128GB of unified memory and up to 4TB of NVMe storage for handling especially large AI programs. Jensen Huang, founder and CEO of Nvidia, announced the new system, along with several other AI offerings, during a keynote speech today at CES, an annual confab for the computer industry held in Las Vegas (you can check out all of the biggest announcements on the WIRED CES live blog). "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," Huang said in a statement released ahead of his keynote. Nvidia says the Digits machine, which stands for "deep learning gpu intelligence training system," will be able to run a single large language model with up to 200 billion parameters, a rough measure of a model's complexity and size. To do this today, you would need to rent space from a cloud provider like AWS or Microsoft, or build a custom system with a handful of chips designed for running AI. If two Digits machines are connected using a proprietary high-speed interconnect link, Nvidia says they will be able to run the most capable version available of Meta's open source Llama model, which has 405 billion parameters. Digits will make it easier for hobbyists and researchers to experiment with models that come close to the basic capabilities of OpenAI's GPT-4 or Google's Gemini in their offices or basements. But the best versions of those proprietary models, housed inside giant data centers owned by Microsoft and Google, are most likely larger as well as more powerful than anything Digits could handle. Nvidia has been one of the largest beneficiaries of the AI boom. Its stock price skyrocketed over the past few years as tech companies clamored to buy vast quantities of the advanced hardware chips it produces, a crucial ingredient for developing cutting-edge AI. The company has proven adept at making hardware and software optimized for AI, and its product roadmap has become an important signal of where the industry is expected to head next. When it's released, Digits will be the most powerful consumer computing hardware Nvidia offers. It already sells a range of chipsets for AI development known as Jetson that start at roughly $250. These can run smaller AI models and either be used like a mini desktop computer or installed on a robot to test different AI programs.

AI-powered desktop for $3,000? This is Nvidia's plan for Project DIGITS

The new machine uses Nvidia's latest "Blackwell" AI chip and will cost $3,000, the company's CEO Jensen Huang revealed earlier this week Earlier this week at CES 2025, Nvidia unveiled a desktop computer called Project DIGITS. The machine uses Nvidia's latest "Blackwell" AI chip and will cost $3,000. It contains a new central processor, or CPU, which Nvidia and MediaTek worked to create. And Nvidia Chief Executive Jensen Huang said on Tuesday that MediaTek will be able to sell the desktop central processor chip the two companies unveiled this week and that Nvidia has undisclosed plans for the chip. Responding to an analyst's question during an investor presentation, Huang said Nvidia tapped MediaTek to co-design an energy-efficient CPU that could be sold more widely. "Now they could provide that to us, and they could keep that for themselves and serve the market. And so it was a great win-win," Huang said. Previously, Reuters reported that Nvidia was working on a CPU for personal computers to challenge the consumer and business computer market dominance of Intel, Advanced Micro Devices (AMD) and Qualcomm. The Project DIGITS computer is not yet a mass-market device. It runs a Linux-based operating system from Nvidia that is used by AI developers, and Huang told analysts those developers are Nvidia's target market with Project DIGITS. But Huang said Nvidia has further plans for its desktop CPU but said he would "wait to tell you" what they are. "You know, obviously we have plans." Later in the question session, Huang said Nvidia believes it can bridge the gap between the Linux operating system that most AI developers use and Microsoft's Windows, which is widely used by consumers, by using a Microsoft technology called Windows Subsystem for Linux that allows a single computer to use both systems. "We're going to make that a mainstream product," Huang said. "We'll support it with all the things that we do to support professional and high-quality software, and the PC (manufacturers) will make it available to end users."

Nvidia announces $3,000 personal AI supercomputer called Digits

If you were looking for your own personal AI supercomputer, Nvidia has you covered. The chipmaker announced at CES it's launching a personal AI supercomputer called Project Digits in May. The heart of Project Digits is the new GB10 Grace Blackwell Superchip, which packs enough processing power to run sophisticated AI models while being compact enough to fit on a desk and run from a standard power outlet (this kind of processing power used to require much larger, more power-hungry systems). This desktop-sized system can handle AI models with up to 200 billion parameters, and has a starting price of $3,000. The product itself looks a lot like a Mac Mini.

Nvidia Unveils Personal AI Supercomputer That Can Run Large AI Models

Nvidia said the device can deliver up to 1 petaflop of AI performance Nvidia unveiled a personal supercomputer equipped with its in-house Grace Blackwell Superchip on Monday at the Consumer Electronics Show (CES) 2025. Dubbed Project Digits, the device can develop, run inference, and deploy large artificial intelligence (AI) models. The personal supercomputer is equipped with the NVIDIA GB10 Grace Blackwell Superchip chipset and delivers up to one petaflop (1,000 trillion floating-point operations per second) of AI performance. The tech giant stated that the personal desktop system will be available in May. In a newsroom post, the company announced the personal AI supercomputer for retail consumers. Calling it the world's smallest AI supercomputer, Nvidia highlighted that Project Digits is equipped with a GB10 Grace Blackwell Superchip SoC. The chipset allows for on-device complex computing as well as the development of processing-intensive applications. However, the company has designed the supercomputer for AI workflows. The chipset features an Nvidia Blackwell GPU with Cuda and Tensor cores and an Arm-based Nvidia Grace CPU with 20 efficiency cores. The chipset was designed in collaboration with MediaTek. Project Digit comes with 128GB of RAM and up to 4TB of NVMe SSD storage. While each device can function independently, Nvidia is also offering its ConnectX networking that allows two Project Digit AI supercomputers to be linked. A linked device can run up to 405 billion parameters AI models, the company claimed. Nvidia claims developers can develop, run, and deploy AI models with up to 200 billion parameters locally with up to one petaflop of AI computing. This would include most of the open-source AI models bar a few such as the Meta Llama 3.1 405B. "With Project Digits, the Grace Blackwell Superchip comes to millions of developers. 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," said Jensen Huang, the CEO of Nvidia. The tech giant said that Project Digits will be available to purchase in May from Nvidia and its partners. The AI supercomputer's price starts at $3,000 (roughly Rs. 2,57,600).

Nvidia brings Blackwell to your desk - Project DIGITS mini PC is more like a mini supercomputer

Nvidia has unveiled Project DIGITS, a brand-new mini PC designed to get AI into the hands of more users through the company's flagship Blackwell hardware. With the GB10 Grace Blackwell Superchip, Nvidia promises a petaflop of AI computing performance, making the device ideal for prototyping, fine-tuning and running large AI models as compute demands increase for businesses and consumers alike. "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," noted Nvidia CEO Jensen Huang. Based on the Grace Blackwell architecture, GB10 Superchip uses a Blackwell GPU with CUDA cores and fifth-generation Tensor Cores and a Grace CPU with 20 power-efficient cores built with the Arm architecture. Nvidia boasts of "best-in-class power efficiency, performance and connectivity." Project DIGITS also includes 128GB of unified DDR5X memory and up to 4TB of NVMe storage. A single supercomputer can handle up to 200-billion-parameter large language models, but two connected via NVIDIA ConnectX networking can handle up to 405-billion-parameter models. Nvidia has set up a dedicated web page for prospective customers to sign up for more information regarding Project DIGITS, dubbed "a Grace Blackwell AI Supercomputer on your desk." The supercomputer will be available from Nvidia and "top partners" from May, and prices will start at $3,000. Further information regarding configurations has not yet been confirmed, and it's unclear whether any further customization can be done beyond SSD storage upgrades.

Nvidia's first desktop PC can run local AI models for $3,000

On Monday, Nvidia announced Project DIGITS, a small desktop computer aimed at researchers, data scientists, and students who want to experiment with AI models -- such as chatbots like ChatGPT and image generators -- at home. The $3,000 device, which contains Nvidia's new GB10 Grace Blackwell Superchip, debuted at CES 2025 in Las Vegas. It will launch in May and can operate as a standalone PC or connect to a Windows or Mac machine. At CES on Monday, Nvidia CEO Jensen Huang described the new system as "a cloud computing platform that sits on your desk." The company also designed Project DIGITS as a bridge between desktop development and cloud deployment. Developers can create and test AI applications locally on Project DIGITS, then move them to cloud services or data centers that use similar Nvidia hardware. The GB10 chip inside the Project DIGITS computer combines an Nvidia Blackwell GPU with a 20-core Grace CPU based on Arm architecture. Nvidia developed the chip in partnership with MediaTek, and it connects to 128GB of memory and up to 4TB of storage inside the Project DIGITS enclosure. Currently, many people use AI models that run on remote data centers due to their computational requirements. Over time, there has been a movement to slim down some AI models so they can run effectively on local, personally owned hardware. Project DIGITS can provide some of that capability at home. A single Project DIGITS unit can reportedly run AI models with up to 200 billion parameters, while two linked units can handle models with 405 billion parameters. In AI models, parameter count roughly corresponds to an AI model's neural network size and complexity, with more parameters requiring more memory and computational power to run. Also, parameter size approximates AI model capability, though different-sized AI models perform differently depending on how they were trained and architected.

Nvidia's Project Digits is a Mini AI Supercomputer That You Can Actually Buy

It costs $3000 and comes with 128GB of unified memory and 4TB of NVMe storage. While Nvidia released its much-anticipated RTX 5090 GPU at CES 2025, what caught my attention was this small, Mac Mini-like supercomputer called DIGITS that can process massive AI workloads. Project DIGITS is Nvidia's effort to bring server-scale compute to your desk. It's a compact computer that packs Nvidia's powerful Blackwell chip and can deliver a petaflop of AI performance at FP4 precision. DIGITS runs Nvidia's DGX OS, which is a Linux-based operating system. It's aimed at developers, academic labs, AI researchers, and students to fine-tune, prototype, and run large AI models for inferencing. Believe it or not, this small computer can run AI models of up to 200B parameters. And when you connect two DIGITS using Nvidia ConnectX, you can run 405B-parameter models. Basically, in such a tiny form factor, you can run Meta's largest Llama 3.1 405B model. Not just that, it comes with 128GB of unified memory and 4TB of NVMe storage. Of course, to fit such a large model, you will have to use models in FP4 data type which is memory-efficient, but may lead to precision loss. As for the hardware, Nvidia's DIGITS supercomputer features the state-of-the-art Blackwell GPU with the latest 5th-gen Tensor cores. And on the CPU side, interestingly, Nvidia has chosen Arm's Cortex cores. It comes with 10x Cortex-X925 and 10x Cortex-A725 CPU cores. Is this Nvidia's answer to Qualcomm's Snapdragon X platform? It's too early to say, but in a way, Nvidia has signaled its entry into the broader computing market. With such a powerful specification, you would expect the supercomputer to have a high price tag, and it does. The DIGITS supercomputer costs $3000 and it will be available in May from Nvidia and its partners. You can click on this link and sign up to receive notifications when the supercomputer is available to purchase.

Nvidia unveils Project Digits personal AI supercomputer for researchers and students

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Nvidia today unveiled Nvidia Project Digits, a personal AI supercomputer that provides AI researchers, data scientists and students worldwide with access to the power of the Nvidia Grace Blackwell platform. Project Digits features the new Nvidia GB10 Grace Blackwell Superchip, offering a petaflop of AI computing performance for prototyping, fine-tuning and running large AI models. The company made the announcement during CEO Jensen Huang's opening keynote at CES 2025, the big tech trade show in Las Vegas this week. With Project Digits, users can develop and run inference on models using their own desktop system, then seamlessly deploy the models on accelerated cloud or data center infrastructure. It is based on a "super secret chip called GB110, the smallest Blackwell we can make," Huang said. "AI will be mainstream in every application for every industry. With Project Digits, the Grace Blackwell Superchip comes to millions of developers," said Huang. "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." GB10 Superchip Provides a Petaflop of Power-Efficient AI Performance The GB10 Superchip is a system-on-a-chip (SoC) based on the Nvidia Grace Blackwell architecture and delivers up to 1 petaflop of AI performance at FP4 precision. GB10 features an Nvidia Blackwell GPU with latest-generation CUDA cores and fifth-generation Tensor Cores, connected via NVLink-C2C chip-to-chip interconnect to a high-performance Nvidia Grace CPU, which includes 20 power-efficient cores built with the Arm architecture. MediaTek, a market leader in Arm-based SoC designs, collaborated on the design of GB10, contributing to its best-in-class power efficiency, performance and connectivity. The GB10 Superchip enables Project DIGITS to deliver powerful performance using only a standard electrical outlet. Each Project DIGITS features 128GB of unified, coherent memory and up to 4TB of NVMe storage. With the supercomputer, developers can run up to 200-billion-parameter large language models to supercharge AI innovation. In addition, using Nvidia ConnectX networking, two Project DIGITS AI supercomputers can be linked to run up to 405-billion-parameter models. Grace Blackwell AI Supercomputing Within Reach With the Grace Blackwell architecture, enterprises and researchers can prototype, fine-tune and test models on local Project DIGITS systems running Linux-based Nvidia DGX OS, and then deploy them seamlessly on Nvidia DGX Cloud, accelerated cloud instances or data center infrastructure. This allows developers to prototype AI on Project DIGITS and then scale on cloud or data center infrastructure, using the same Grace Blackwell architecture and the Nvidia AI Enterprise software platform. Project Digits users can access an extensive library of Nvidia AI software for experimentation and prototyping, including software development kits, orchestration tools, frameworks and models available in the Nvidia NGC catalog and on the Nvidia Developer portal. Developers can fine-tune models with the Nvidia NeMo framework, accelerate data science with Nvidia Rapids libraries and run common frameworks such as PyTorch, Python and Jupyter notebooks. To build agentic AI applications, users can also harness Nvidia Blueprints and Nvidia NIM microservices, which are available for research, development and testing via the Nvidia Developer Program. When AI applications are ready to move from experimentation to production environments, the Nvidia AI Enterprise license provides enterprise-grade security, support and product releases of Nvidia AI software. Availability Project Digits will be available in May from Nvidia and top partners, starting at $3,000. "By making Llama models open source, we're committed to democratizing access to cutting-edge AI technology. With Project Digits, developers can harness the power of Llama locally, unlocking new possibilities for innovation and collaboration," said Ahmad Al-Dahle, Head of GenAI at Meta, in a statement. "Advancing AI requires tools that empower researchers to experiment at scale, speed and precision. Nvidia's Project Digits represents a significant leap forward. I'm excited to see how 128GB in such a small form factor can advance the future of enterprise AI," said Silvio Savarese, Chief Scientist at Salesforce, in a statement. "At Hugging Face, we want to make it easy for developers to build their own AI. Nvidia's Project Digits will empower AI builders to build and run their own Gen AI models and systems at the edge. With 128GB of unified memory, AI builders can run 200B parameter models locally, and connect multiple Project Digits systems to scale from there. I can't wait to see what the Hugging Face community will build with Nvidia Project Digits," said Je Boudier, Head of Product at Hugging Face, in a statement. "Nvidia's Project Digits is a powerhouse you can hold in the palm of your hand. With two Project Digits units, developers can easily work with AI models up to 405B parameters in size. We can't wait to see the apps people will build with this," said Michael Chiang, cofounder of Ollama, in a statement.

Did the launch go unnoticed? Nvidia's Jensen Huang unveils world's smallest AI supercomputer; this revolutionary system could change how you work in a big way; here's how

In a pretty recent development it has been known that Nvidia CEO Jensen Huang unveiled the smallest AI computer of the world till date and it is being claimed that such a revolutionary system could actually change the fact that how an individual could actually work in a pretty big way. At CES 2025, Nvidia eventually introduced Project DIGITS which is a revolutionary personal AI supercomputer and is designed to democratize advanced AI development, reported Interesting Engineering. Reports revealed that it is being priced at $3,000 and is launching in the month of May while the device will be targeting researchers, data scientists and students seeking powerful AI computing capabilities. According to Interesting Engineering, the Project DIGITS system is actually powered by the GB10 Grace Blackwell Superchip while delivering a petaflop of AI performance in a compact desktop form factor. The key specifications include 128GB of unified memory whereas at the same time, up to 4TB of NVMe storage and the ability to run AI models with up to 200 billion parameters. Reportedly it is being asserted that by linking the two systems, numerous users can even manage models with 405 billion parameters. Developed in collaboration with MediaTek, the supercomputer runs on Nvidia's Linux-based DGX OS and integrates seamlessly with NVIDIA's AI ecosystem, asserted Interesting Engineering. Adding onto that, it also supports popular development tools like PyTorch, NVIDIA NeMo and RAPIDS while enabling smooth model prototyping, fine-tuning and deployment across local and cloud environments. Nvidia CEO Jensen Huang eventually put an emphasis on the potential of the device to gradually empower millions of developers by placing an AI supercomputer on every researcher's desk, noted Interesting Engineering. At CES 2025, Nvidia eventually introduced Project DIGITS which is a revolutionary personal AI supercomputer and is designed to democratize advanced AI development. The Project DIGITS system is actually powered by the GB10 Grace Blackwell Superchip while delivering a petaflop of AI performance in a compact desktop form factor.

NVIDIA Unveils "Project DIGITS" At CES 2025; AI Supercomputer Which Can Power OpenAI's ChatGPT-4o At Your Fingertips

NVIDIA has unveiled its newest "AI supercomputer," called "Project DIGITS," which is said to be the world's most compact device to offer computational power that was previously deemed impossible. Well, Team Green certainly made huge strides at the CES 2025 keynote, and when it comes to "AI," the firm surely nailed its releases. Starting with the mainstream RTX Blackwell GPUs and working up its way into computing products, NVIDIA indeed showed why it is the "boss" of the tech markets, and their Project DIGITS unveiling surprises us the most. For those unaware, this particular project can be called a mini AI supercomputer that has a size that makes it easy to use on your desk, but the computational power here is enough to cater to LLMs such as OpenAI's GPT-4o and many more. Diving a bit into the technicals, NVIDIA's DIGITS AI system comes with a new and unique GB10 Grace Blackwell Superchip. The chip utilizes NVIDIA's Blackwell GPU, one petaFLOPS FP4 AI compute power, and an ARM-based Grace CPU, which features a 20-core configuration. Interestingly, this is the first time NVIDIA and MediaTek have collaborated on a SoC apart from the automotive segment, and Jensen especially credited the Taiwanese SoC manufacturer for their expertise on the project. AI will be mainstream in every application for every industry. With Project DIGITS, the Grace Blackwell Superchip comes to millions of developers. 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. - NVIDIA's CEO Jensen Huang Apart from this, the DIGITS supercomputer is equipped with 128 GB low-power DDR5X memory, along with a 4TB SSD for storage. All the components are interlinked through NVIDIA's C2C interconnect, which allows NVIDIA to leverage architectural capabilities to bring in tremendous power. Speaking of power, the DIGITS system is said to run up to 200-billion-parameter large language models, and by using NVIDIA's ConnectX networking, linking two of these systems allows us to run 405-billion-parameter models, which is fascinating. Well, DIGITS is like having a large-scale supercomputer at your fingertips, and it does show us how far we have evolved in the realm of AI compute. In terms of release date and availability, NVIDIA DIGITS is expected to be available by May 2025, coming in with a price tag of $3,000, which is certainly pricey for an end user, but judging by the performance, the system is indeed worth every penny.

Beyond the Cloud: Nvidia's Mini Supercomputer Brings AI on-Premise | PYMNTS.com

Nvidia's new mini artificial intelligence supercomputer has the potential to put unprecedented computing power into the hands of researchers, developers and academics. However, experts say it can also be an enabler for business innovation, especially for those in heavily regulated industries who want to own their own AI systems for security purposes. Project Digits is the personal supercomputer with Nvidia's new GB10 Grace Blackwell Superchip, combining a GPU and CPU. It delivers a petaflop of AI computing power, or 1 quadrillion calculations per second, and can run AI models with up to 200 billion parameters. With a $3,000 price tag, Project Digits represents a fundamental shift in AI development. By bringing supercomputer-grade AI capabilities to individuals at a relatively affordable price, Nvidia is betting that the next breakthrough in AI might come not from a massive research lab but from an office cubicle, a student's dorm room or a researcher's home office. "Nvidia's Project Digits represents a major leap forward in democratizing AI capabilities," DeepBrain AI Chief Financial Officer Michael Jung told PYMNTS in an interview. "The compact form factor and immense computational power make it a game changer, not just for researchers, but also for businesses." "For businesses, this means the ability to develop advanced AI models without needing access to traditional supercomputing resources," he added. "It lowers the barrier to entry for small and medium enterprises looking to integrate AI-driven insights into their operations." The mini supercomputer "has the potential to broaden AI innovation across industries, allowing organizations of all sizes to harness the power of generative AI to improve efficiency, create more personalized customer experiences, and stay competitive in the digital economy," he said. Each mini supercomputer comes equipped with 128GB of unified memory and can be expanded. For those needing even more power, two units can be linked together to handle models with up to 405 billion parameters. It also uses a standard wall electrical outlet. Nvidia said it has balanced performance with power efficiency in this innovation. Project Digits is part of a trend in organizations building, deploying and owning their own AI systems, AI Squared co-founder Jacob Renn told PYMNTS in an interview. "While proprietary models serve many customers well, organizations with stringent compliance and security requirements often face barriers to their adoption," Renn said. "Project Digits addresses this gap by enabling businesses to train and deploy advanced AI systems outside the cloud, even in fully disconnected environments." Hitachi Ventara Chief Technology Officer for AI Jason Hardy told PYMNTS in an interview that while he would not go so far as to call it a game changer, Project Digits is a "significant enabling event" for business. "Accessibility of this technology -- specifically GPUs -- has always been limited due to cost, infrastructure scale and power demand," he said. But now, Nvidia is making this technology more accessible to the masses. "It's important to note that this won't replace the need for data center or large-scale compute environments; however, it will enable the further development of new and creative ideas that can utilize GPU resources," Hardy said. The supercomputer can bridge the gap between personal development and enterprise deployment. Developers can prototype and fine-tune their AI models locally, then deploy them to cloud or data center infrastructure. Smaller companies can now prototype AI solutions without massive cloud computing budgets. Academic researchers can run sophisticated models without waiting for shared computing resources. Students can learn by experimenting with state-of-the-art AI models on their own machines. Online Games CEO Marin Christian Ovidiu told PYMNTS in an interview that Project Digits makes "powerful AI easy to use and cheaper. Small businesses can train and use AI models without big data centers or high costs. For example, in games, we can make smarter characters and better worlds faster." Project Digits also uses less power, which helps the planet since AI is notorious for being a power guzzler, he said.

Nvidia reveals Project Digits to power personal AI supercomputers at CES 2025 | TechCrunch

Nvidia founder and CEO Jensen Huang had an extensive CES 2025 address, detailing everything from Nvidia's next set of GPUs, its plans for embracing the next era of robotics and automotive innovation, and the launch of its own AI world models. And before he ended his keynote, Huang had one more reveal in store: Project Digits. Nvidia has shrunk down its Grace Blackwell hardware platform to fit into consumer devices, making its research- and data science- oriented chips more accessible to students and researchers. They'll still have to pay $3,000 for these machines, which are targeted to launch in May from "top partners." Nvidia has yet to offer more details, but it's a step in the right direction for this kind of processing power. Follow along with the rest of Nvidia's reveals and our coverage of CES via our liveblog.

NVIDIA Project DIGITS is the World's Smallest AI Supercomputer, 1 Petaflop of AI performance

NVIDIA Project DIGITS is described as the 'World's Smallest AI Supercomputer,' a desk-sized rig with the new NVIDIA GB10 Grace Blackwell Superchip. This thing is an absolute beast, offering a staggering 1 Petaflop of AI computing performance at FP4 precision, and it's capable of running 200B, that's 200 billion, parameter models. "AI will be mainstream in every application for every industry. With Project DIGITS, the Grace Blackwell Superchip comes to millions of developers," said Jensen Huang, founder and CEO of NVIDIA. "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." The new GB10 Superchip is a system-on-chip (SoC) based on the NVIDIA Grace Blackwell architecture. It sports the latest generation of CUDA Cores and fifth-generation Tensor Cores, connected via an NVLink-C2C interconnect. NVIDIA collaborated with Arm-based SoC specialists MediaTek on the GB10 design, promising best-in-class power efficiency and performance. As we're talking about an AI supercomputer, the final Project DIGITS AI PC will run on a "standard electrical outlet." Each Project DIGITS desktop AI Supercomputer will feature 128GB of unified memory and 4TB of NVMe storage. And with NVIDIA ConnectX networking, two Project DIGITS AI Supercomputers can link up and run up to 405-billion-parameter models. Project DIGITS users will have access to all of NVIDIA's AI software, the Linux-based NVIDIA DGX OS, and the ability to deploy seamlessly on NVIDIA DGX Cloud. Project DIGITS will be available in May 2025 from NVIDIA and its top partners, starting from $3,000.

Here's how small Nvidia's $3,000 Digits supercomputer looks in person

One of the biggest announcements in Nvidia CEO Jensen Huang's CES keynote was the small "Project Digits" AI supercomputer, and if you want to get an idea of just how tiny the $3,000 machine is in real life, we snapped a couple photos of the device under glass today at the show. Take a look: we've captured the front of a Digits computer in the photo at the top of this post, and below this paragraph is a photo of the back featuring the computer's ports. I really like the textured design. The Digits computers will come with Nvidia's GB10 Grace Blackwell Superchip, which offers "a petaflop of AI computing performance for prototyping, fine-tuning and running large AI models," according to Nvidia's press release. It also includes a GPU built with Nvidia's Blackwell architecture, 128GB of unified memory, and up to 4TB of NVMe SSD storage. This isn't a computer for most people; Nvidia says that that Project Digits is intended to give "AI researchers, data scientists and students worldwide with access to the power of the NVIDIA Grace Blackwell platform." It definitely isn't something I will ever buy.

Nvidia Fits Blackwell GPU Into a Mini Desktop System

Nvidia has steered clear of creating its own PCs. But at CES, the company came a little closer by showing off a mini desktop system. Dubbed "Project DIGITS," the product is set to arrive as a small, square-shaped package no different from other mini PCs. It'll also run Nvidia's DGX OS, the company's custom version of Ubuntu Linux. "In essence, it's a personal supercomputer for your desk," Nvidia product marketing director Allen Bourgoyne told reporters during a briefing. But Project DIGITS isn't meant to be a standalone product. Rather, it's designed to work as a peripheral that can connect to a customer's main desktop PC, running heavy AI-focused workloads on the side. Nvidia designed the mini computer to appeal to AI developers, data scientists, and students looking to get their hands on the company's Blackwell GPU, which can cost between $30,000 to $40,000 per unit. In contrast, DIGITS will be sold starting at $3,000 through Nvidia and its partners this May. Project DIGITS appears to be a scaled-down version of Blackwell, offering 1 petaflop of AI performance, instead of 10 or 20 petaflops. Specifically, the product carries the GB10 Blackwell Supership along with 128GB of unified system memory, enabling it to support AI models up to 200 billion parameters in size -- similar to OpenAI's GPT-3. DIGITS also promises to run without any extra cooling or power needs. Nvidia says the hardware can connect to a regular electrical socket, giving owners a way to run large AI models, without always relying on third-party servers hosted over the internet. Instead, DIGITS can be used as a testing bed to fine-tune or prototype AI models or programs before scaling them out to a data center. The hardware itself can support up to 4TB of NVMe storage. "In addition, using Nvidia ConnectX networking, two Project DIGITS AI supercomputers can be linked to run up to 405-billion-parameter models," the company adds. Interested customers can go to Nvidia.com to sign up for notifications on when Project DIGITS officially launches. The announcement arrives weeks after Nvidia launched a budget-focused mini computer in the $249 Jetson Orin Nano Super, which is also designed mainly to run AI-based applications.

NVIDIA debuts mini AI supercomputer Project DIGITS for $3,000

Built on the robust NVIDIA Grace Blackwell platform, Project DIGITS delivers unprecedented AI capabilities, allowing users to prototype, fine-tune, and deploy large-scale AI models -- all from a desktop system. At the heart of Project DIGITS is the revolutionary NVIDIA GB10 Grace Blackwell Superchip, offering an extraordinary petaflop of AI performance at FP4 precision. This system-on-a-chip (SoC) combines the cutting-edge Blackwell GPU -- featuring the latest CUDA cores and Tensor Cores -- with a high-efficiency Grace CPU built on Arm architecture. The GB10 Superchip leverages NVLink-C2C for seamless chip-to-chip communication, enabling unparalleled performance. The collaboration between NVIDIA and MediaTek, a leader in Arm-based SoC technology, has resulted in a power-efficient design that packs significant computational power into a device that runs on a standard electrical outlet. Project DIGITS includes 128GB of unified memory and up to 4TB of NVMe storage, making it capable of handling AI models with as many as 200 billion parameters. By linking two DIGITS systems via NVIDIA ConnectX networking, users can push this capability further, managing models with up to 405 billion parameters.

Nvidia's Project Digits is a 'personal AI supercomputer'

At the Consumer Electronics Show in Las Vegas, Nvidia unveiled Project Digits, a "personal AI supercomputer" that provides access to the company's Grace Blackwell hardware platform in a compact form factor. Designed for AI researchers, data scientists, and students, Project Digits packs Nvidia's new GB10 Grace Blackwell Superchip, which delivers up to a petaflop of computing performance for prototyping, fine-tuning, and running AI models. Nvidia claims that Project Digits can run models up to 200 billion parameters in size.

Nvidia's new supercomputer is 1000-times more powerful than a laptop and can fit in your bag

Nvidia has introduced 'Project Digits', a mini PC combining a Blackwell graphics card and a Grace processor on a single chip, offering immense processing power compact enough for portability. The device, equipped with 128GB memory and 4TB SSD storage, supports running complex AI models locally, potentially revolutionizing research capabilities for developers and data scientists.Nvidia has developed a new mini PC that boasts power comparable to a small supercomputer while remaining portable enough to fit in a bag, reported Live Science. Dubbed as 'Project Digits', the new mini PC is aimed at developers, researchers, students, and data scientists. The device utilizes Nvidia's GB10 Grace Blackwell Superchip, combining a Blackwell graphics card and a Grace processor on a single chip. It also features 128 gigabytes of memory and 4 terabytes of SSD storage. This setup provides approximately 1,000 times the power of an average laptop, enabling users to run complex AI models locally, eliminating the need for large data centers. Project Digits offers 1 petaFLOP of computing power, significantly less than the world's fastest supercomputers, but substantially more than typical PCs and laptops. "NVIDIA's Project DIGITS enables researchers in robotics, computer vision and autonomous systems to experiment, fine-tune and scale solutions faster than ever -- all while fitting on your desk," said Raquel Urtasun, a University of Toronto computer science professor and founder of self-driving car company Waabi. With Project Digits, researchers can run large language models, including those with up to 200 billion parameters. Connecting two devices extends this capability to 405 billion parameters. While the final design is still in progress, Nvidia plans a May launch with a price tag of around $3,000. Interested individuals can register their interest with Nvidia. Meanwhile, Nvidia also showcased the new GeForce RTX 50 series for desktop and laptop computers based on Blackwell chip architecture as its most advanced consumer GPUs. PCs enhanced with RTX chips for AI capabilities will be available from an array of manufacturers including Acer, Dell, HP, Lenovo, Razer and Samsung, according to Nvidia. The chipmaker also displayed an AI PC priced at $1,299, built with the $549 RTX chip at the starting point of the new GPU line-up. Along with rapid rendering of rich gameplay action, Nvidia AI technology will enable the creation of characters that perceive, plan and act like human players, according to Nvidia. Such autonomous characters are being integrated into games including "PUBG: Battlegrounds", according to Nvidia. Huang also introduced a family foundation models open to the world for advancing "physical AI" that enables robots to understand and engage in real-world tasks.

Nvidia Project Digits: A Linux-powered desktop for AI developers

What's making the headlines at CES 2025 are AI-powered TVs, new smart home gadgets, and fresh laptop releases. For my money, though, the big news from CES is Nvidia Project Digits. This revolutionary desktop AI supercomputer is designed to bring unprecedented computing power to artificial intelligence (AI) developers, researchers, and students. And, by the way, it will be running Nvidia's DGX OS, a customized Ubuntu Linux 22.04 distro. As you might guess, DGX OS is a Linux distro designed with system-specific optimizations and configurations, drivers, and diagnostic and monitoring tools to provide a fully supported version of Linux for running AI, machine learning, and analytics applications on Nvidia DGX Supercomputers. Also: The best tech we've seen at CES so far On top of that, Nvidia will also provide AI software development kits; orchestration tools; Nvidia NGC catalog frameworks and models; the Nvidia NeMo framework for fine-tuning models; and Nvidia Rapids libraries for data science acceleration. Of course, as an Ubuntu Linux system at heart, you can run Ubuntu and Linux software. So, if you want to, you can play Doom on it. That's probably the first I'll do if I get my hands on one of these devices. Now, in a box that appears to be about the size of a Mac mini, Nvidia's Project Digits PC promises to bring a petaflop of AI performance to your desktop. A petaflop, for those of you who don't hang out in supercomputer land, is equal to 1,000,000,000,000,000 (one quadrillion) floating-point operations per second (flops). Until 2008, when IBM rolled out its Roadrunner supercomputer, no one had ever hit that speed. Soon, you could have that level of computing performance in your home office. Even today, the latest Top 500 SuperComputer List has computers that squeak in with just over two petaflops. Mind you, these computers also need over a thousand cores to pull that trick off. Oh, and they all run Linux. Project Digits will be almost Top 500-fast and is powered by Nvidia's band's new GB10 Grace Blackwell Superchip. With the Nvidia AI software stack preinstalled and 128GB of memory, developers can prototype, fine-tune, and infer large AI models of up to 200B parameters locally and then seamlessly deploy to the data center or cloud. Also: The best robotics and AI tech of CES The Grace Blackwell Superchip is named after Grace Hopper, the famed computer scientist, United States Navy rear admiral, and the "Mother of Cobol". In addition, the chip's name honors David Harold Blackwell, an American mathematician who made significant contributions to game theory, probability theory, information theory, and statistics, and was the first Black scholar to be inducted into the National Academy of Sciences. In this superpowered chip, you'll find an ARM-based Grace CPU featuring 10 Cortex-X925 and 10 Cortex-A725 cores. That's 20 cores in all. The CPU is backed up by a Blackwell GPU equipped with Nvidia's latest CUDA and RT cores. The PC has 128 GBs of RAM and up to 4 TBs of flash storage to put all this chip firepower to good work. Nvidia promises that AI developers will be able to work with models of up to 200 billion parameters on a single unit. For more demanding tasks, you can link two Project Digits machines together to handle models with up to 405 billion parameters. Also: ZDNET joins CNET Group to award the Best of CES, and you can submit your entry now Nvidia's CEO, Jensen Huang, emphasized Project Digits' transformative potential, stating: "Placing an AI supercomputer on the desks of every data scientist, AI researcher, and student empowers them to engage with and shape the age of AI." With a starting price of $3,000, Project Digits aims to make high-performance AI development more accessible to a broader range of users, from small enterprises to schools. At that price point, I expect to see Project Digits desktops in homes. This Linux-powered system, set to launch in May 2025, promises to reshape the landscape of AI development by offering data center-level performance in a compact, desk-friendly form factor. I, for one, will be doing my darndest to get my hands on one.

Jensen Huang Unveils $3000 'Personal AI Supercomputer' The Size Of A Small Book: 'It Runs The Entire Nvidia AI Stack' - NVIDIA (NASDAQ:NVDA)

On Monday, at CES 2025, Nvidia Corp. NVDA CEO Jensen Huang introduced the company's $3,000 "personal AI supercomputer," a compact, high-performance machine designed to run advanced AI models right from your desk. What Happened: During his keynote speech at the CES conference in Las Vegas, Huang announced the launch of Digits, a desktop-sized personal AI supercomputer that will be available in May 2025. Price starting at $3,000, Digits is powered by Nvidia's proprietary GB10 Grace Blackwell superchip which is specifically designed to accelerate the computations required for AI workloads. See Also: Nvidia 5000 Series, Product Updates Make It Top Semiconductor Pick Ahead Of Jensen Huang's CES Keynote: Analyst The system is compact, about the size of a small book, yet packed with impressive specs -- 128GB of unified memory and up to 4TB of NVMe storage, offering immense processing power. With this setup, Digits can handle a single AI model of up to 200 billion parameters, which would typically require cloud services like AWS or custom-built data centers. "It runs the entire Nvidia AI stack," Huang said during his keynote, adding, "All of Nvidia's software runs on this, DGX cloud runs on this. This ability will allow anyone with the system to run some of the most sophisticated models currently available without relying on cloud resources. Subscribe to the Benzinga Tech Trends newsletter to get all the latest tech developments delivered to your inbox. Why It's Important: During his CES 2025 keynote, Huang also introduced the new RTX 5000 GPU series, laptops featuring the RTX 50-series, and the Grace Blackwell NVLink 72 system. Huang also announced that Toyota will base its next-generation vehicles on Nvidia Drive AGX Orin, using the safety-certified Nvidia DriveOS operating system to deliver advanced assistance features. Industry experts and Wall Street analysts have shared varied opinions on Nvidia's ambitious tech roadmap presented at CES 2025, with mixed reactions focusing especially on its AI and autonomous driving projects. Price Action: Nvidia's stock rose by 3.43% on Monday, closing at $149.43. During the pre-market session on Tuesday, it saw a further increase of 1.12%, reaching $151.1. Year-to-date, the stock has gained 9.93%, according to data from Benzinga Pro. Check out more of Benzinga's Consumer Tech coverage by following this link. Read Next: Nvidia Soars, AMD Stalls: AI Race Heats Up At CES 2025 Disclaimer: This content was partially produced with the help of AI tools and was reviewed and published by Benzinga editors. Photo courtesy: Shutterstock NVDANVIDIA Corp$151.591.45%Overview Rating:Good75%Technicals Analysis1000100Financials Analysis600100WatchlistOverviewMarket News and Data brought to you by Benzinga APIs

Nvidia unveils cut-down Grace-Blackwell Superchip

Tuned for running chunky models on the desktop with 128GB of RAM, custom Ubuntu CES Nvidia has announced a desktop computer powered by a new GB10 Grace-Blackwell superchip and equipped with 128GB of memory to give AI developers, researchers, and students the tools they need to run large models on the desktop. Code-named Project Digits and announced at the annual CES super-event in Las Vegas today, the $3,000 system was developed in collaboration with MediaTek, and is powered by an Arm-based Grace CPU and Blackwell GPU that, based on renders released by Nvidia, appear to reside in a single SoC. The box will ship with a special brew of Ubuntu Linux pre-configured to take advantage of the hardware. Project Digits vaguely resembles an Intel NUC mini-PC in terms of size. Nvidia hasn't detailed the GB10's specs in full but has said the machine it powers delivers a full petaFLOP of AI performance. But before you get too excited about the prospect of a small form factor desktop outperforming Nvidia's A100 tensor core GPU, know that the machine's performance was measured on sparse 4-bit floating point workloads. Specs we've seen suggest the GB10 features a 20-core Grace CPU and a GPU that packs manages a 40th the performance of the twin Blackwell GPUs used in Nvidia's GB200 AI server. The machine nonetheless packs rather more power than an AI PC powered by processors from Intel, AMD, or Qualcomm, but will struggle to compete with a workstation packing Nvidia's current flagship workstation card, the RTX 6000 Ada. That accelerator boasts 1.45 petaFLOPS of sparse FP/INT8 performance, roughly triple the performance we think Project Digits will deliver (500 teraFLOPS) at that precision. Feeding those flops are 128GB of LPDDR5x memory. According to Allen Bourgoyne, Nvidia's director of product marketing for enterprise platforms, the decision to equip the system with this much memory was intentional to make working with large AI models more accessible. Nvidia claims Project Digits will be able to support models up to 200 billion parameters in size. However, to fit such models into the machine they will need to be compressed to 4-bits, a concept you can learn more about in our hands-on guide. Running larger models will be possible thanks to onboard ConnectX networking that Nvidia says will allow two of these computers to be connected so they can run models with up to 405 billion parameters. That puts Meta's Llama 3.1 405B in play, again at 4-bits. For reference, if you wanted to run that same model at 4-bits on existing workstation hardware you'd need at least five 48GB GPUs. It's unclear how Project Digits will perform when running such models, as at the time of writing Nvidia hadn't disclosed memory bandwidth, a key metric for inference performance of large language models. From the renders shown to the press prior to the Monday night CES keynote at which Nvidia announced the box, the system appeared to feature six LPDDR5x modules. Assuming memory speeds of 8,800 MT/s we'd be looking at around 825GB/s of bandwidth which wouldn't be that far off from the 960GB/s of the RTX 6000 Ada. For a 200 billion parameter model, that'd work out to around eight tokens/sec. Again, that's just speculation, as the full spec-sheet for the system wasn't available prior to CEO Jensen Huang's CES Keynote. Along with AI inferencing, Nvidia also expects Project Digits will be well suited to model experimentation, fine tuning, data science, and other edge applications. Along with an ample supply of memory, Project Digits will come equipped with 4TB of NVMe storage, which should be plenty for most open models, especially those that have been quantized down to 4-bits. Customers can expect to get their hands on a table-top superchip beginning in May though, as we mentioned earlier it won't come cheap, with systems starting at $3,000. Project Digits is not Nvidia's first foray onto the desktop. The GPU giant has offered its Jetson dev kits for years and debuted a new model - the Orin Nano Super - in December 2024. The new machine is essentially just a grown-up Jetson with a whole lot more computational grunt. Nvidia hasn't said whether it'll offer the GB10 to other PC makers - a tantalizing prospect that would shake up the market. In its current form, this machine looks more like it is aimed at getting folks comfortable with Nvidia's more powerful Grace-Blackwell Superchips like the GB200 and GB200 NVL4 we've looked at previously. The reason for this is simple: the Arm Neoverse V2 cores used in Nvidia's Grace CPUs thus far were announced more than two years ago and were engineered with datacenter workloads in mind. That's not to say Nvidia won't one day market the GB10 for gaming and graphics centric products, like the company has already done with its Tegra line of SoCs. If the GB10 is using a more modern CPU core than the original Grace CPU, it certainly wouldn't be out of the realm of possibility. ®

Nvidia just unveiled a $3,000 Mac mini clone for AI computing

Project Digits is a supercomputer with a tiny square footprint. Just hours after Dell decided all on its own to rename its laptop line with Pro and Pro Max monikers, Nvidia also took a page from Apple's playbook with its new "personal AI supercomputer." No, it's not called the Nvidia mini, but it does have a certain simpatico with the Mac mini. Nvidia didn't share the exact specs for what it's calling Project Digits, but the device fit neatly in CEO Jensen Huang's palm during its unveiling. Next to a monitor and keyboard (above), it appears to be slightly bigger than the Mac mini with a boxier and more industrial design. Nvidia didn't provide benchmarks for the GB10 chip, but did say it's capable of a petaflop of FP4 floating point performance and able to "run up to 200-billion-parameter large language models," likely beyond the capabilities of the $599 Mac mini. However, Nvidia isn't selling it to just anyone. The goal of Project Digits, Huang said, is to put "an AI supercomputer on the desks of every data scientist, AI researcher and student." To that end, the computer starts at $3,000 and comes with a 20-core GB10 Grace Blackwell Superchip and 128GB of unified memory. Configuring a Mac mini with the M4 Pro chip, which has a 14-core CPU, and 64GB of RAM, costs $2,499 with 1TB of storage. A 1TB Mac Studio fitted with a 24-core M2 Ultra and 128GB of RAM brings the price to $4,799. While it takes several M4 Mac minis to even reach a teraflop of performance, the M2 Ultra in the Mac Studio already tops 20 teraflops. And Apple is expected to upgrade that machine to the M4 family of processors sometime this year, which will obviously bring a major performance boost. And we assume the power draw will be many times that of the Mac mini or Mac Studio (or Mac Pro for that matter). Of course, we're comparing Apples to oranges here. Nvidia's Mac mini clone isn't meant for everyday work. Digits is kitted out with Nvidia's full AI software enterprise platform, including "an extensive library of Nvidia AI software for experimentation and prototyping, including software development kits, orchestration tools, frameworks and models."

Nvidia's mini 'desktop supercomputer' is 1,000 times more powerful than a laptop -- and it can fit in your bag

Project Digits offers a petaFLOP of power in an incredibly compact chassis. This is roughly 1,000 times more powerful than a laptop and 1,000 less powerful than the fastests computers on the planet. (Image credit: Getty Images/Qi Yang) Scientists have created a new mini PC that is almost as powerful as a supercomputer but can fit in your bag. The new device, dubbed "Project Digits," is designed for developers, researchers, students and data scientists who work with artificial intelligence (AI). Its uses include running AI models that would have previously required tapping into massive data centers via the cloud, Nvidia's CEO Jensen Huang announced at CES 2025 in Las Vegas. Although the product design has not yet been finalized, it will be small enough to fit on your desk or even in your bag. The device is powered by an Nvidia GB10 Grace Blackwell Superchip, which houses separate, linked components on a single chip to reduce the time it takes to move data between them. The superchip features an Nvidia Blackwell graphics card and an Nvidia Grace processor, packaged with 128 gigabytes of memory and 4 terabytes of SSD storage. Related: Google 'Willow' quantum chip has solved a problem the best supercomputer would have taken a quadrillion times the age of the universe to crack Altogether, the device is approximately 1,000 times more powerful than the average laptop. Sign up for the Live Science daily newsletter now Get the world's most fascinating discoveries delivered straight to your inbox. Contact me with news and offers from other Future brandsReceive email from us on behalf of our trusted partners or sponsorsBy submitting your information you agree to the Terms & Conditions and Privacy Policy and are aged 16 or over.A mini PC that's 1000-times more powerful than your PC or laptop "NVIDIA's Project DIGITS enables researchers in robotics, computer vision and autonomous systems to experiment, fine-tune and scale solutions faster than ever -- all while fitting on your desk," said Raquel Urtasun, a professor of computer science at the University of Toronto and founder of Waabi, a self-driving car company, in a statement. Waabi uses Nvidia's technology in its fleet of self-driving trucks. "I'm excited to see what breakthroughs Project DIGITS will enable." Supercomputing power is measured in floating point operations per second (FLOPS). The most powerful supercomputers in the world deliver a little over 1,000 petaFLOPS of power (1 quintillion FLOPS). This makes them 1 million times more powerful than laptops, according to IBM. Project Digits, by contrast, can provide 1 petaFLOPS of power. It won't match the very best supercomputers, but it's way more powerful than most desktop PCs and laptops and can fit into a considerably smaller chassis. RELATED STORIES -- World's 2nd-fastest supercomputer runs largest-ever simulation of the universe -- Google's Sycamore quantum computer chip can now outperform the fastest supercomputers, new study suggests -- Japan to start building 1st 'zeta-class' supercomputer in 2025, 1,000 times more powerful than today's fastest machines Using this "desktop supercomputer," researchers can run large language models -- generative AI tools like ChatGPT -- that use up to 200 billion parameters, while two Project DIGITS devices can be connected to achieve 405 billion parameters. For reference, GPT-3.5, which powered the first version of ChatGPT when it launched in November 2022, was approximately 175 billion parameters in size, with each parameter being a variable that controls how a model processes and generates text. The device's design has not been finalized yet. Nvidia representatives did not share an image of the prototype, but they said it was set to launch in May for approximately $3,000 -- with people able to register their interest in buying one.