# NVIDIA DGX GB300 AI factory infrastructure for the era of AI reasoning. ## Where to Buy [Get DGX](https://www.nvidia.com/en-us/data-center/get-dgx.md) [Talk to Us](#contact-us) [Datasheet](https://resources.nvidia.com/en-us-dgx-systems/dgx-gb300-datasheet) | [Specifications](#quick-specs) | [Documentation](https://docs.nvidia.com/dgx/) Overview ## AI Factory Infrastructure, the NVIDIA Way NVIDIA DGX™ GB300 is the highest-performing, largest-scale AI system available for enterprises. Built with [NVIDIA Grace™ Blackwell Ultra Superchips](https://www.nvidia.com/en-us/data-center/gb300-nvl72.md) and scalable up to thousands, DGX GB300 is a rack-scale, liquid-cooled system designed to fit into modern data centers using [NVIDIA MGX™](https://nvidianews.nvidia.com/news/nvidia-contributes-blackwell-platform-design-to-open-hardware-ecosystem-accelerating-ai-infrastructure-innovation) racks. With DGX GB300, the world’s leading enterprises can break through performance bottlenecks and equip their organization with an infrastructure solution capable of solving any problem. ### Build AI Factories for the Era of AI Reasoning Learn how NVIDIA DGX GB300 is purpose-built to handle any workload across the develop-to-deploy pipeline. [Read the Datasheet](https://resources.nvidia.com/en-us-dgx-systems/dgx-gb300-datasheet) ### Accelerating AI Innovation for Naval Postgraduate School (NPS) Learn how NPS utilizes its NVIDIA DGX GB300 system and NVIDIA Mission Control™ software to solve challenges in the public sector. [Read the Announcement](https://blogs.nvidia.com/blog/naval-postgraduate-school-ai/) Features ## Democratizing Hyperscaler AI ### Built on NVIDIA Grace Blackwell Ultra Superchips Powered by [Grace Blackwell Ultra Superchips](https://www.nvidia.com/en-us/data-center/gb300-nvl72.md), NVIDIA DGX GB300 is designed to maximize performance for training, post-training, and test-time inference, boosting dense FP4 performance by 1.5x and attention performance by 2x over [NVIDIA DGX GB200](https://www.nvidia.com/en-us/data-center/dgx-gb200.md). ### World-Class Infrastructure Resiliency [NVIDIA Mission Control](https://www.nvidia.com/en-us/data-center/mission-control.md) streamlines AI operations, from workloads to infrastructure, with world-class expertise delivered as software. Powering NVIDIA Blackwell data centers, Mission Control provides full-stack intelligence for infrastructure resilience, enabling every enterprise to run AI factories with hyperscale efficiency. ### Designed for Modern Data Centers NVIDIA DGX SuperPOD™ with DGX GB300 systems eliminates the guesswork from deploying large-scale AI infrastructure with a simple, easy-to-deploy rack architecture designed to take advantage of the latest advancements in data center engineering. Specifications ## NVIDIA DGX GB300 Specifications | | | | --- | --- | | GPU | 72x NVIDIA Blackwell Ultra GPUs, 36x NVIDIA Grace CPUs | | CPU Cores | 2,592 Arm Neoverse V2 cores | | GPU Memory | Bandwidth | 20 TB | Up to 576 TB/s | | Total Fast Memory | 37 TB | | Performance | FP4 Tensor Core: 1440 PFLOPS | 1080 PFLOPS\* FP8/FP6 Tensor Core: 720 PFLOPS\*\* | | Networking | 72x OSFP single-port NVIDIA® ConnectX®-8 VPI with 800 Gb/s NVIDIA InfiniBand   18x dual-port NVIDIA® BlueField®-3 VPI with 200 Gb/s NVIDIA InfiniBand and Ethernet | | NVIDIA NVLink Switch System | 9x L1 NVIDIA NVLink™ Switches | | Management Network | Host baseboard management controller (BMC) with RJ45 | | Software | NVIDIA Mission Control NVIDIA AI Enterprise NVIDIA DGX OS / Ubuntu | | Enterprise Support | Three-year business-standard hardware and software support | \*Specification shown in sparse | dense. \*\*Without sparsity. Offers ## Delivering Supercomputing to Every Enterprise ### Introducing NVIDIA Mission Control **Integrated orchestration software for AI factories at scale.** NVIDIA Mission Control streamlines AI factory operations, from workloads to infrastructure, with world-class expertise delivered as software. It powers NVIDIA Blackwell data centers, bringing instant agility for inference and training while providing full-stack intelligence for infrastructure resilience. Every enterprise can run AI with hyperscale efficiency, simplifying and accelerating AI experimentation. [Run Models, Automate the Essentials](https://www.nvidia.com/en-us/data-center/mission-control.md) ### NVIDIA DGX Platform **The proven standard for enterprise AI.** Built from the ground up for enterprise AI, the NVIDIA DGX platform, featuring [NVIDIA DGX SuperPOD](https://www.nvidia.com/en-us/data-center/dgx-superpod.md), combines the best of NVIDIA software, infrastructure, and expertise in a modern, unified AI development solution. [Explore the NVIDIA DGX Platform](https://www.nvidia.com/en-us/data-center/dgx-platform.md) ### NVIDIA DGX Enterprise Support **Maximize the value of your NVIDIA DGX B300.** NVIDIA Enterprise Services provides support, education, and infrastructure specialists for your NVIDIA DGX infrastructure. With NVIDIA experts available at every step of your AI journey, Enterprise Services can help you get your projects up and running quickly and successfully. [Learn More About NVIDIA Enterprise Services](https://www.nvidia.com/en-us/data-center/dgx-support.md) ### DLI for NVIDIA DGX **Exclusive training offers for NVIDIA DGX customers.** NVIDIA DGX customers can learn how to achieve cutting-edge breakthroughs with AI faster with exclusive technical training offered by the AI experts at [NVIDIA’s Deep Learning Institute (DLI)](https://www.nvidia.com/en-us/training.md). [Check Out DLI for NVIDIA DGX Training](https://resources.nvidia.com/en-us-dgx-systems/dgx-training-special-offer-2023) ## Get Started ### NVIDIA DGX GB300 is Available Now Deploy NVIDIA DGX GB300 today on premises, in a colocation facility, or in the cloud through one of our partners. [Get DGX](https://www.nvidia.com/en-us/data-center/get-dgx.md) #### Discover the Benefits of the NVIDIA DGX Platform NVIDIA DGX is the proven standard on which enterprise AI is built. [Learn More](https://www.nvidia.com/en-us/data-center/dgx-platform.md) #### Need Help Selecting the Right Product or Partner? Talk to an NVIDIA product specialist about your professional needs. [Talk to Us](#contact-us) ## DGX GB300 Quick Specs | | | | --- | --- | | GPU | 72x NVIDIA Blackwell Ultra GPUs, 36x NVIDIA Grace CPUs | | CPU Cores | 2,592 Arm Neoverse V2 cores | | GPU Memory | Bandwidth | 20 TB | Up to 576 TB/s | | Total Fast Memory | 37 TB | | Performance | FP4 Tensor Core: 1440 PFLOPS | 1080 PFLOPS\* FP8/FP6 Tensor Core: 720 PFLOPS\*\* | \*Specification shown in sparse | dense. \*\*Without sparsity. [View NVIDIA DGX GB300 Datasheet](https://resources.nvidia.com/en-us-dgx-systems/dgx-gb300-datasheet)