Nvidia rtx pro 5000 72gb blackwell gpu targets desktop agentic artificial intelligence workloads

Nvidia has made the rtx pro 5000 72gb blackwell gpu generally available, giving developers, designers and engineers more local compute and memory headroom for agentic and generative artificial intelligence workloads. The card expands on the existing 48gb model with higher performance and capacity aimed at large models, complex 3d scenes and demanding simulations.

Nvidia has released the rtx pro 5000 72gb blackwell gpu into general availability, expanding desktop options for developers, engineers and designers working on demanding agentic and generative artificial intelligence workflows. The new configuration targets memory-hungry tasks such as large language models, multimodal artificial intelligence agents and complex simulation workloads, arriving as demand for blackwell class compute continues to grow. Users can now choose between the 72gb variant and the existing rtx pro 5000 48gb model so artificial intelligence developers can align hardware more closely with different budgets and project needs.

The card is built on the nvidia blackwell architecture, which is designed for high throughput across artificial intelligence, neural rendering and simulation with multi workload scheduling and other architectural updates. The rtx pro 5000 72gb helps address memory bottlenecks in agentic artificial intelligence systems that must keep multiple models, data sources and code formats resident in gpu memory. The gpu offers 2,142 TOPS of AI performance and includes 72GB of ultrafast GDDR7 memory – a 50% increase over the 48GB model – enabling developers to train, fine tune and prototype larger models directly on their workstations. This local capacity is positioned to help teams maintain data privacy, low latency and cost efficiency by serving more artificial intelligence workloads without relying on data center infrastructure.

Nvidia highlights performance gains in both artificial intelligence and graphics focused workflows. In industry standard benchmarks for generative artificial intelligence, the RTX PRO 5000 72GB offers 3.5x the performance of prior-generation NVIDIA hardware for image generation, and 2x the performance of prior-generation hardware for text generation. In creative rendering pipelines using engines like arnold, chaos v ray, blender, d5 render and redshift, the RTX PRO 5000 72GB slashes render times by up to 4.7x, and for computer aided engineering and product design it offers more than 2x graphics performance. Early adopters such as infinitform are using the gpu to accelerate generative artificial intelligence based engineering design for customers including yamaha motor and nasa, while versatile media is applying the 72gb card to virtual production, where its memory capacity supports massive 3d scenes and complex lighting in real time. The rtx pro 5000 72gb blackwell gpu is now shipping through partners including ingram micro, leadtek, unisplendour and xfusion, with broader global system builder availability planned for early next year.

58

Impact Score

OpenAI launches Artificial Intelligence deployment consulting unit

OpenAI has created a new consulting and deployment business aimed at helping enterprises build and roll out Artificial Intelligence systems. The move mirrors a similar push by Anthropic and signals a broader effort by model providers to capture more of the enterprise services market.

SK Group warns DRAM shortages could curb memory use

SK Group chairman Chey Tae-won warned that customers may reduce memory consumption through infrastructure and software optimization if DRAM suppliers fail to raise output. Demand from Artificial Intelligence data centers is keeping the market tight as memory makers weigh expansion against the long timelines for new fabs.

BitUnlocker bypasses TPM-only Windows 11 BitLocker

Intrinsec disclosed BitUnlocker, a downgrade attack that can bypass TPM-only Windows 11 BitLocker protections with physical access to a machine. The technique abuses a flaw in Windows recovery and deployment components and relies on older trusted boot code.

Micron samples 256 GB DDR5 9200 MT/s RDIMM server modules

Micron has begun sampling 256 GB DDR5 RDIMM server modules built on its 1-gamma technology to key ecosystem partners. The company positions the new modules as a higher-speed, more power-efficient option for scaling next-generation Artificial Intelligence and HPC infrastructure.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.