NVIDIA Puts Grace Blackwell on Every Desk and at Every AI Developer’s Fingertips
NVIDIA has unveiled Project DIGITS, a personal AI supercomputer powered by the new GB10 Grace Blackwell Superchip. This desktop system delivers up to 1 petaflop of AI performance and can run models with up to 200 billion parameters. The GB10 Superchip combines a Blackwell GPU with a Grace CPU featuring 20 Arm-based cores, developed in collaboration with MediaTek.
Project DIGITS includes 128GB of unified memory and up to 4TB of NVMe storage. Two units can be linked to handle 405-billion-parameter models. The system runs on Linux-based NVIDIA DGX OS and allows seamless deployment to cloud or data center infrastructure. Users can access NVIDIA's AI software library, including SDKs, frameworks, and tools from the NGC catalog.
The system will launch in May, starting at $3,000, targeting AI researchers, data scientists, and students.
NVIDIA ha presentato Project DIGITS, un supercomputer personale basato sull'IA alimentato dal nuovo GB10 Grace Blackwell Superchip. Questo sistema desktop offre prestazioni IA fino a 1 petaflop e può eseguire modelli con fino a 200 miliardi di parametri. Il Superchip GB10 combina una GPU Blackwell con una CPU Grace dotata di 20 core basati su Arm, sviluppata in collaborazione con MediaTek.
Project DIGITS include 128GB di memoria unificata e fino a 4TB di storage NVMe. Due unità possono essere collegate per gestire modelli con 405 miliardi di parametri. Il sistema funziona con NVIDIA DGX OS basato su Linux e consente un'implementazione fluida su infrastrutture cloud o data center. Gli utenti possono accedere alla libreria software IA di NVIDIA, inclusi SDK, framework e strumenti del catalogo NGC.
Il sistema verrà lanciato a maggio, a partire da $3.000, rivolto a ricercatori IA, scienziati dei dati e studenti.
NVIDIA ha presentado Project DIGITS, un superordenador personal de IA impulsado por el nuevo GB10 Grace Blackwell Superchip. Este sistema de escritorio ofrece hasta 1 petaflop de rendimiento en IA y puede ejecutar modelos de hasta 200 mil millones de parámetros. El Superchip GB10 combina una GPU Blackwell con una CPU Grace con 20 núcleos basados en Arm, desarrollada en colaboración con MediaTek.
Project DIGITS incluye 128GB de memoria unificada y hasta 4TB de almacenamiento NVMe. Se pueden enlazar dos unidades para manejar modelos con 405 mil millones de parámetros. El sistema opera con el NVIDIA DGX OS basado en Linux y permite un despliegue fluido en infraestructura de nube o centros de datos. Los usuarios pueden acceder a la biblioteca de software IA de NVIDIA, que incluye SDK, marcos y herramientas del catálogo NGC.
El sistema se lanzará en mayo, comenzando desde $3,000, dirigido a investigadores de IA, científicos de datos y estudiantes.
NVIDIA는 Project DIGITS를 발표했습니다. 이는 새로운 GB10 Grace Blackwell Superchip으로 구동되는 개인 AI 슈퍼컴퓨터입니다. 이 데스크탑 시스템은 최대 1 페타플롭의 AI 성능을 제공하며 최대 2000억 개의 매개변수를 가진 모델을 실행할 수 있습니다. GB10 슈퍼칩은 Arm 기반의 20개 코어를 가진 Grace CPU와 함께 Blackwell GPU를 결합합니다. 이는 MediaTek과 협력하여 개발되었습니다.
Project DIGITS는 128GB의 통합 메모리와 최대 4TB의 NVMe 스토리지를 포함합니다. 두 개의 장치는 4050억 개의 매개변수를 가진 모델을 처리하기 위해 연결될 수 있습니다. 이 시스템은 리눅스 기반의 NVIDIA DGX OS에서 작동하며 클라우드 또는 데이터 센터 인프라에 원활하게 배포할 수 있습니다. 사용자는 SDK, 프레임워크 및 NGC 카탈로그의 도구를 포함한 NVIDIA의 AI 소프트웨어 라이브러리에 접근할 수 있습니다.
이 시스템은 5월에 출시되며 가격은 $3,000부터 시작하여 AI 연구자, 데이터 과학자 및 학생들을 대상으로 하고 있습니다.
NVIDIA a dévoilé Project DIGITS, un superordinateur personnel alimenté par IA, propulsé par le nouveau GB10 Grace Blackwell Superchip. Ce système de bureau offre jusqu'à 1 petaflop de performances en IA et peut exécuter des modèles comportant jusqu'à 200 milliards de paramètres. La puce Superchip GB10 combine un GPU Blackwell avec un CPU Grace comprenant 20 cœurs basés sur Arm, développée en collaboration avec MediaTek.
Project DIGITS comprend 128 Go de mémoire unifiée et jusqu'à 4 To de stockage NVMe. Deux unités peuvent être reliées pour gérer des modèles avec 405 milliards de paramètres. Le système fonctionne sous NVIDIA DGX OS basé sur Linux et permet un déploiement fluide sur des infrastructures cloud ou de centres de données. Les utilisateurs peuvent accéder à la bibliothèque de logiciels IA de NVIDIA, y compris des SDK, des frameworks et des outils du catalogue NGC.
Le système sera lancé en mai, à partir de $3,000, ciblant les chercheurs en IA, les scientifiques des données et les étudiants.
NVIDIA hat Project DIGITS vorgestellt, einen persönlichen KI-Supercomputer, der vom neuen GB10 Grace Blackwell Superchip angetrieben wird. Dieses Desktop-System bietet bis zu 1 Petaflop KI-Leistung und kann Modelle mit bis zu 200 Milliarden Parametern ausführen. Der GB10 Superchip kombiniert eine Blackwell GPU mit einer Grace CPU, die über 20 Arm-basierte Kerne verfügt, entwickelt in Zusammenarbeit mit MediaTek.
Project DIGITS umfasst 128 GB einheitlichen Speicher und bis zu 4 TB NVMe-Speicher. Zwei Einheiten können verbunden werden, um Modelle mit 405 Milliarden Parametern zu bearbeiten. Das System läuft auf dem NVIDIA DGX OS auf Linux-Basis und ermöglicht eine nahtlose Bereitstellung auf Cloud- oder Rechenzentrumsinfrastrukturen. Nutzer können auf die KI-Softwarebibliothek von NVIDIA zugreifen, die SDKs, Frameworks und Tools aus dem NGC-Katalog umfasst.
Das System wird im Mai auf den Markt kommen, beginnend bei 3.000 $, und richtet sich an KI-Forscher, Datenwissenschaftler und Studenten.
- Introduction of powerful AI supercomputer for desktop use at competitive $3,000 price point
- Capability to run large 200B-parameter AI models
- Integration with existing NVIDIA cloud and data center infrastructure
- Efficient power consumption (runs on standard electrical outlet)
- Extensive software ecosystem access included
- None.
Insights
NVIDIA's Project DIGITS marks a watershed moment in democratizing AI computing. The GB10 Grace Blackwell Superchip, delivering 1 petaflop of AI performance in a desktop form factor, fundamentally shifts the landscape of AI development. At
The technical specifications are revolutionary - 128GB unified memory, 4TB NVMe storage and capability to run 200-billion-parameter models locally transforms the development workflow. The ability to scale to 405-billion-parameter models through linking systems creates a compelling bridge between desktop and data center computing.
This product strategically positions NVIDIA to capture the growing AI developer market while protecting its enterprise business through seamless integration with DGX Cloud and data center solutions. The collaboration with MediaTek adds credibility to the power efficiency claims and expands NVIDIA's ecosystem in the Arm space.
The timing and pricing of Project DIGITS are masterfully calculated to expand NVIDIA's market dominance. At
The addressable market is substantial - targeting data scientists, AI researchers and students represents millions of potential users. The product creates a new category between consumer GPUs and enterprise systems, potentially generating a fresh revenue stream while protecting high-end DGX sales through differentiated features and support.
This launch could significantly impact competitors in the AI accelerator market, particularly those targeting the development and research segments. The seamless cloud integration strategy creates powerful lock-in effects, potentially increasing NVIDIA's cloud service revenues long-term.
Project DIGITS represents a significant revenue opportunity for NVIDIA. Conservative estimates suggest a potential market of several million units annually. At
The strategic value extends beyond direct hardware sales. The ecosystem lock-in through NVIDIA AI Enterprise software licenses and cloud services creates recurring revenue opportunities. The seamless integration with DGX Cloud could accelerate enterprise cloud adoption, potentially generating high-margin subscription revenue.
This move strengthens NVIDIA's competitive moat in AI computing while opening new market segments. The stock market should respond positively to this expansion of NVIDIA's total addressable market and the potential for sustained growth in both hardware and software/services revenue streams.
NVIDIA Project DIGITS With New GB10 Superchip Debuts as World’s Smallest AI Supercomputer Capable of Running 200B-Parameter Models
LAS VEGAS, Jan. 06, 2025 (GLOBE NEWSWIRE) -- CES—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.
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.
“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.”
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
About NVIDIA
NVIDIA (NASDAQ: NVDA) is the world leader in accelerated computing.
For further information, contact:
Kelly Musgrave
NVIDIA Corporation
+1-650-421-3748
kmusgrave@nvidia.com
Certain statements in this press release including, but not limited to, statements as to: the benefits, impact, and performance of NVIDIA’s products, services, and technologies, including NVIDIA Project DIGITS, NVIDIA Grace Blackwell, NVIDIA GB10 Grace Blackwell Superchip, NVIDIA Blackwell GPU, NVIDIA CUDA cores and fifth-generation Tensor Cores, NVIDIA NVLink-C2C chip-to-chip interconnect, NVIDIA Grace CPU, NVIDIA DGX Cloud, NVIDIA AI Enterprise software platform, NVIDIA NeMo, NVIDIA RAPIDS libraries, NVIDIA Blueprints, and NVIDIA NIM microservices; AI being mainstream in every application for every industry; with Project DIGITS, the Grace Blackwell Superchip coming to millions of developers; and placing an AI supercomputer on the desks of every data scientist, AI researcher and student empowering them to engage and shape the age of AI are forward-looking statements that are subject to risks and uncertainties that could cause results to be materially different than expectations. Important factors that could cause actual results to differ materially include: global economic conditions; our reliance on third parties to manufacture, assemble, package and test our products; the impact of technological development and competition; development of new products and technologies or enhancements to our existing product and technologies; market acceptance of our products or our partners’ products; design, manufacturing or software defects; changes in consumer preferences or demands; changes in industry standards and interfaces; unexpected loss of performance of our products or technologies when integrated into systems; as well as other factors detailed from time to time in the most recent reports NVIDIA files with the Securities and Exchange Commission, or SEC, including, but not limited to, its annual report on Form 10-K and quarterly reports on Form 10-Q. Copies of reports filed with the SEC are posted on the company's website and are available from NVIDIA without charge. These forward-looking statements are not guarantees of future performance and speak only as of the date hereof, and, except as required by law, NVIDIA disclaims any obligation to update these forward-looking statements to reflect future events or circumstances.
Many of the products and features described herein remain in various stages and will be offered on a when-and-if-available basis. The statements above are not intended to be, and should not be interpreted as a commitment, promise, or legal obligation, and the development, release, and timing of any features or functionalities described for our products is subject to change and remains at the sole discretion of NVIDIA. NVIDIA will have no liability for failure to deliver or delay in the delivery of any of the products, features or functions set forth herein.
© 2025 NVIDIA Corporation. All rights reserved. NVIDIA, the NVIDIA logo, ConnectX, CUDA, DGX, Project DIGITS, NGC, NVIDIA Grace, NVIDIA NeMo, NVIDIA NIM, NVIDIA RAPIDS and NVLink are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries. Other company and product names may be trademarks of the respective companies with which they are associated. Features, pricing, availability and specifications are subject to change without notice.
A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/7da82266-2579-4d9d-a5e6-265e07938d77
FAQ
When will NVIDIA's Project DIGITS (NVDA) be available and at what price?
What are the key specifications of NVIDIA's GB10 Grace Blackwell Superchip?
What is the maximum AI model size that Project DIGITS can handle?
What software platforms are compatible with NVIDIA's Project DIGITS?
How does NVIDIA Project DIGITS integrate with cloud services?
