NVIDIA Spectrum-X 800G Ethernet reduces latency and jitter for AI infrastructure.
NVIDIA introduced Blackwell Ultra, the latest advancement in the Blackwell AI factory platform, designed to support AI reasoning. NVIDIA Blackwell Ultra enhances training and test-time scaling inference, enabling organizations to improve accuracy and accelerate applications such as AI reasoning, agentic AI, and physical AI.
Built on the Blackwell architecture introduced a year ago, Blackwell Ultra includes the NVIDIA GB300 NVL72 rack-scale solution and the NVIDIA HGX B300 NVL16 system. The GB300 NVL72 delivers 1.5x more AI performance than the NVIDIA GB200 NVL72, as well as increases Blackwell’s revenue opportunity by 50x for AI factories, compared with those built with NVIDIA Hopper.
NVIDIA Blackwell Ultra enables AI reasoning
The NVIDIA GB300 NVL72 connects 72 Blackwell Ultra GPUs and 36 Arm. Neoverse-based NVIDIA Grace CPUs in a rack-scale design, acting as a single massive GPU built for test-time scaling. With the NVIDIA GB300 NVL72, AI models can utilize increased compute capacity to process complex requests more efficiently, improving response accuracy and consistency.
GB300 NVL72 is expected to be available on NVIDIA DGX Cloud, a managed AI platform on leading clouds that optimizes performance with software, services and AI expertise for evolving workloads. NVIDIA DGX SuperPOD with DGX GB300 systems uses the GB300 NVL72 rack design to provide customers with a pre-configured AI infrastructure.
The NVIDIA HGX B300 NVL16 features 11x faster inference on large language models, 7x more compute and 4x larger memory compared with the Hopper generation to deliver breakthrough performance for the most complex workloads, such as AI reasoning.
In addition, the Blackwell Ultra platform is ideal for applications including:
- Agentic AI applies advanced reasoning and iterative planning to independently address complex, multistep problems. AI agent systems go beyond instruction-following. They can reason, plan and take actions to achieve specific goals.
- Physical AI, enabling companies to generate synthetic, photorealistic videos in real time for the training of applications such as robots and autonomous vehicles at scale.
NVIDIA scale-out infrastructure for optimal performance
Advanced scale-out networking is a critical component of AI infrastructure that can deliver top performance while reducing latency and jitter.
Blackwell Ultra systems seamlessly integrate with the NVIDIA Spectrum-X Ethernet and NVIDIA Quantum-X800 InfiniBand platforms, with 800 Gb/s of data throughput available for each GPU in the system, through an NVIDIA ConnectX-8 SuperNIC. This provides advanced remote direct memory access capabilities, helping AI factories and cloud data centers efficiently process AI reasoning models with reduced bottlenecks.
NVIDIA BlueField-3 DPUs, included in Blackwell Ultra systems, support multi-tenant networking, flexible GPU compute allocation, faster data access, and real-time cybersecurity threat monitoring.
Global technology leaders embrace Blackwell Ultra
Blackwell Ultra-based products are expected to be available from partners starting from the second half of 2025.
Cisco, Dell Technologies, Hewlett Packard Enterprise, Lenovo and Supermicro are expected to deliver a wide range of servers based on Blackwell Ultra products, in addition to Aivres, ASRock Rack, ASUS, Eviden, Foxconn, GIGABYTE, Inventec, Pegatron, Quanta Cloud Technology (QCT), Wistron and Wiwynn.
Cloud service providers Amazon Web Services, Google Cloud, Microsoft Azure and Oracle Cloud Infrastructure and GPU cloud providers CoreWeave, Crusoe, Lambda, Nebius, Nscale, Yotta and YTL will be among the first to offer Blackwell Ultra-powered instances.
NVIDIA software optimizes AI performance and scalability
The entire NVIDIA Blackwell product portfolio is supported by the full-stack NVIDIA AI platform. The NVIDIA Dynamo open-source inference framework scales up reasoning AI services, delivering leaps in throughput while reducing response times and model serving costs by providing the most efficient solution for scaling test-time compute.
NVIDIA Dynamo is AI inference-serving software designed to enhance efficiency in AI factories deploying reasoning AI models. It manages inference communication across thousands of GPUs and uses disaggregated serving to separate the processing and generation phases of large language models on different GPUs. This approach enables independent optimization of each phase and improves GPU resource utilization.
Blackwell systems are ideal for running new NVIDIA Llama Nemotron Reason models and the NVIDIA AI-Q Blueprint, supported in the NVIDIA AI Enterprise software platform for production-grade AI. NVIDIA AI Enterprise includes NVIDIA NIM microservices, as well as AI frameworks, libraries and tools that enterprises can deploy on NVIDIA-accelerated clouds, data centers and workstations.
The Blackwell platform builds on NVIDIA’s ecosystem of powerful development tools, NVIDIA CUDA-X libraries, over 6 million developers and 4,000+ applications scaling performance across thousands of GPUs.
For more information, visit nvidia.com.
