Nvidia’s (NVDA) tiniest supercomputer officially hits the market on Wednesday. The DGX Spark, which Nvidia said offers data center-class performance, packs the company’s GB10 Grace Blackwell superchip, as well as its ConnectX-7 networking capabilities and software stack.
The idea is to provide smaller businesses and developers with access to an AI computing system without requiring them to spend thousands on renting AI data center services or buying their own AI servers.
The Spark is part of a new class of computer Nvidia is rolling out with third-party partners, including ASUS (2357.TW) and Dell (DELL), which will allow customers to develop and use AI models on their own local devices.
Nvidia said the Spark can be outfitted with up to 128GB of storage, which should help when running massive AI models.
The company also has a larger, more powerful DGX Station, which runs on Nvidia’s GB300 Grace Blackwell Ultra desktop superchip.
But don’t expect to grab a Spark or Station and start running your video games or other apps. The system runs on Nvidia’s own Linux-based DGX OS and its AI software stack and is specifically designed for building and running AI models.
Nvidia also said users can connect two Spark systems to allow for even larger AI models with up to 405 billion parameters.
The Spark and Station are designed to complement Nvidia’s existing AI offerings, enabling users to prototype AI models before deploying them more widely.
Nvidia holds the pole position in the AI chip race thanks to both its powerful processors and CUDA software service.
In addition to its desktop systems, the company continues to ink massive deals with AI companies, including a $100 billion investment in OpenAI (OPAI.PVT) that will see the ChatGPT developer purchase 10 gigawatts of GPUs.
Last month, Nvidia signed a deal that will see CoreWeave (CRWV) purchase $6.3 billion worth of GPUs from the chip giant.
The company is also providing GPUs to Elon Musk’s xAI (XAAI.PVT), Amazon (AMZN), Google (GOOG, GOOGL), Meta (META), Microsoft (MSFT), and a slew of other tech behemoths — not to mention OpenAI and Oracle’s (ORCL) joint Stargate Project venture.
Email Daniel Howley at dhowley@yahoofinance.com. Follow him on X/Twitter at @DanielHowley.
Click here for the latest technology news that will impact the stock market
Read the latest financial and business news from Yahoo Finance
Nvidia’s (NVDA) tiniest supercomputer officially hits the market on Wednesday. The DGX Spark, which Nvidia said offers data center-class performance, packs the company’s GB10 Grace Blackwell superchip, as well as its ConnectX-7 networking capabilities and software stack.
The idea is to provide smaller businesses and developers with access to an AI computing system without requiring them to spend thousands on renting AI data center services or buying their own AI servers.
The Spark is part of a new class of computer Nvidia is rolling out with third-party partners, including ASUS (2357.TW) and Dell (DELL), which will allow customers to develop and use AI models on their own local devices.
Nvidia said the Spark can be outfitted with up to 128GB of storage, which should help when running massive AI models.
The company also has a larger, more powerful DGX Station, which runs on Nvidia’s GB300 Grace Blackwell Ultra desktop superchip.
But don’t expect to grab a Spark or Station and start running your video games or other apps. The system runs on Nvidia’s own Linux-based DGX OS and its AI software stack and is specifically designed for building and running AI models.
Nvidia also said users can connect two Spark systems to allow for even larger AI models with up to 405 billion parameters.
The Spark and Station are designed to complement Nvidia’s existing AI offerings, enabling users to prototype AI models before deploying them more widely.
Nvidia holds the pole position in the AI chip race thanks to both its powerful processors and CUDA software service.
In addition to its desktop systems, the company continues to ink massive deals with AI companies, including a $100 billion investment in OpenAI (OPAI.PVT) that will see the ChatGPT developer purchase 10 gigawatts of GPUs.
Last month, Nvidia signed a deal that will see CoreWeave (CRWV) purchase $6.3 billion worth of GPUs from the chip giant.
The company is also providing GPUs to Elon Musk’s xAI (XAAI.PVT), Amazon (AMZN), Google (GOOG, GOOGL), Meta (META), Microsoft (MSFT), and a slew of other tech behemoths — not to mention OpenAI and Oracle’s (ORCL) joint Stargate Project venture.
Email Daniel Howley at dhowley@yahoofinance.com. Follow him on X/Twitter at @DanielHowley.
Click here for the latest technology news that will impact the stock market
Read the latest financial and business news from Yahoo Finance
