NVIDIA has introduced a new series of systems powered by its Blackwell technology, engineered to empower businesses to set up their own AI and data centers, thereby strengthening their capacity for innovative AI advancements.
These tech systems include the NVIDIA MGX modular reference design platform—which now supports Blackwell designs—and the recently revealed NVIDIA GB200 NVL2 platform. These platforms operate with single or multiple GPUs, x86 or Grace-based processors, and air- or liquid-cooling options.
NVIDIA reported that its GB200 NVL2 platform will ramp up data processing speeds up to 18x faster with an 8x enhancement in energy efficiency as opposed to using x86 CPUs. This performance improvement is credited to the new Blackwell architecture.
Analyst QuickTake: The latest update to Blackwell technology was launched in March 2024 with the Blackwell GB200l, which reportedly offers 25x lower cost and energy consumption compared to its predecessors, the H100 and A100 GPUs. Additionally, in April 2024 , NVIDIA introduced the RTX A400 and A1000 GPUs as part of its efforts to enhance GenAI hardware.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.