Skip to content

CoreWeave First to Offer NVIDIA Blackwell RTX PRO 6000 GPUs at Cloud Scale

3 min read
CoreWeave First to Offer NVIDIA Blackwell RTX PRO 6000 GPUs at Cloud Scale

Table of Contents

CoreWeave's Blackwell GPU Cloud: Powering the Next Wave of AI

CoreWeave has become the first AI-focused cloud provider to make NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs available at scale through its cloud platform. The launch expands access to NVIDIA’s latest Blackwell-based hardware via on-demand cloud instances, allowing customers to deploy advanced AI and graphics workloads without owning or operating dedicated infrastructure.

Invest in top private AI companies before IPO, via a Swiss platform:

Swiss Securities | Invest in Pre-IPO AI Companies
Own a piece of OpenAI, Anthropic & the companies changing the world. Swiss-regulated investment platform for qualified investors. Access pre-IPO AI shares through Swiss ISIN certificates.

By offering Blackwell GPUs through a cloud model, CoreWeave enables organizations to access high-performance compute resources without the capital expenditure and operational complexity associated with building private data centers. The instances are designed to support inference and multimodal workloads, including applications that process combinations of text, images, audio, and video, such as generative AI systems and interactive design tools.

Revolutionary Performance Improvements

The RTX PRO 6000 Blackwell GPU introduces substantial performance improvements compared with earlier generations. According to NVIDIA’s published specifications, the GPU delivers up to 5.6 times higher throughput for large language model inference and up to 3.5 times faster performance for text-to-video workloads, depending on configuration and use case.

In practical terms, these improvements can reduce inference latency and increase the number of concurrent requests supported by a given deployment. This is particularly relevant for production environments where responsiveness and predictable performance are required for user-facing AI services, including conversational systems, media generation, and interactive visualization.

The GPU is optimized for AI models with up to approximately 70 billion parameters, a range commonly used in production systems where a balance between model capability, cost, and latency is required. By hosting these GPUs in its cloud environment, CoreWeave allows customers to deploy such models without managing hardware provisioning, networking, cooling, or ongoing maintenance.

Complete Blackwell Ecosystem Integration

The introduction of RTX PRO 6000 instances forms part of a broader Blackwell-based infrastructure offering within CoreWeave’s platform. The provider now supports multiple tiers of NVIDIA Blackwell systems, including the NVIDIA GB200 NVL72 for large-scale training and dense inference workloads, the NVIDIA HGX B200 platform for configurable high-performance deployments, and RTX PRO 6000 instances for production-oriented use cases.

This tiered approach allows customers to select hardware configurations based on workload requirements. Large training jobs and high-density inference can be deployed on GB200 systems, while HGX B200 supports flexible, high-end workloads. RTX PRO 6000 instances are positioned for scenarios where performance is required without the scale or complexity of the largest GPU clusters.

Democratizing Advanced AI Computing

Making RTX PRO 6000 Blackwell GPUs available through a cloud service shifts access to advanced AI compute from ownership-based models to usage-based consumption. Developers and enterprises can provision high-performance GPU resources as needed, scale capacity up or down in response to demand, and avoid long-term infrastructure commitments.

This model lowers the barrier to entry for teams building AI applications that require modern GPU capabilities but do not justify dedicated hardware investment. By offering Blackwell-based GPUs as a cloud service, CoreWeave extends access to current-generation AI compute to a broader range of organizations, supporting experimentation, deployment, and scaling within a managed cloud environment.

CoreWeave Becomes the First AI Cloud Provider to Offer NVIDIA RTX PRO 6000 Blackwell GPU at Scale
/PRNewswire/ -- CoreWeave, Inc. (Nasdaq: CRWV) (“CoreWeave”), the AI Hyperscaler™, today announced it is the first cloud platform to make NVIDIA RTX PRO 6000…
View Full Page

Related Posts