Semiconductor giant Nvidia (NVDA) unveiled two new personal AI supercomputers at the much-awaited GTC 2025 event held yesterday. The supercomputers are named DGX Spark and DGX Station, with the former considered as the world’s smallest AI supercomputer. Interestingly, both supercomputers are designed to empower users’ desktops with Nvidia’s Grace Blackwell architecture, commonly used to power advanced data centers. These systems are mostly used by AI developers, researchers, data scientists, and students to build, train, and deploy AI models on the edge or in the cloud.
Here’s More About DGX Supercomputers
The DGX Spark, which started accepting pre-orders yesterday, is equipped with Nvidia’s GB10 Grace Blackwell Superchip and is capable of delivering up to 1,000 trillion operations per second (TOPS). The DGX Spark was previously referred to as DIGITS during the CES event held earlier this year. The DGX Spark is expected to work seamlessly with a large number of reasoning AI models, including those from China’s DeepSeek, Meta’s (META) LLaMA, and Alphabet (GOOGL) Google’s Gemini.
Meanwhile, the newly announced DGX Station is a more superior system and larger in size. It features Nvidia’s GB300 Grace Blackwell Ultra Desktop Superchip and offers a massive 784GB of coherent memory space, aimed to accelerate AI training and inferencing capabilities. Orders for the DGX Station are expected to being later this year through partners, including ASUS, Dell (DELL), HP (HPE), and Supermicro Computer (SMCI).
While unveiling the two personal AI supercomputers at the GTC Event, CEO Jensen Huang said, “This is what computers should look like, and this is what computers will run in the future.” He added that there will be a lot of AI agents in the future, and their operations will be powered by this new line of supercomputers.
At the same time, Nvidia also unveiled two new microchips called Blackwell Ultra and Rubin AI at the GTC developer conference. The new chips will help in building advanced AI models offering higher performance and delivery per second.
Is NVDA Stock a Good Buy Right Now?
Wall Street remains highly bullish about Nvidia’s stock trajectory amid the AI boom. On TipRanks, NVDA stock has a Strong Buy consensus rating based on 39 Buys versus three Hold ratings. Also, the average Nvidia price target of $177.23 implies 53.5% upside potential from current levels. In the past year, NVDA stock has gained 29.2%.
Questions or Comments about the article? Write to editor@tipranks.com