Following a delay, Nvidia is ready to release the DGX Station, a desktop-like computer that can run AI models locally, bringing AI data center-like performance to your home or office.
At the company’s annual GTC event, Nvidia revealed that PC manufacturers are starting to accept orders for their DGX Station units. The company’s website offers a catalog of the six upcoming models from six companies: Asus, Dell, HP, Gigabyte, MSI, and server provider Supermicro.
(Credit: Nvidia)
All the units come with their own names and are packed in desktop tower cases. However, pricing is unclear. The vendors are asking interested customers to fill out a form with their contact information. The companies will then follow up with more details. Nvidia also declined to reveal pricing, but told journalists in a briefing that buyers can expect the DGX station units to begin shipping out within weeks.
(Credit: Gigabyte)
DGX Station: A Pumped-Up Spark
Introduced a year ago, the DGX Station is basically the more powerful big brother of the DGX Spark, a $4,000 mini PC that can also run AI models locally. The portable DGX Spark features a smaller GB10 Grace Blackwell chip and 128GB of RAM, enabling it to run AI models with up to 200 billion parameters.
In contrast, the DGX Station features a larger Nvidia GB300 chip and a staggering 748GB of “coherent memory” shared between the processing and graphics portions. Nvidia says the computing power is enough to run even larger, more advanced AI models that span up to 1 trillion parameters.
(Credit: Supermicro)
But like DGX Spark, the larger DGX Station is almost certainly going to be expensive and is being advertised toward enterprises. The DGX Station was supposed to arrive last year, but it was pushed back to this spring. In a press briefing, Nvidia indicated that packing the GB300 chip and its motherboard into a desktop case was a challenge that required more time.
Get Our Best Stories!
Your Daily Dose of Our Top Tech News
By clicking Sign Me Up, you confirm you are 16+ and agree to our Terms of Use and Privacy
Policy.
Thanks for signing up!
Your subscription has been confirmed. Keep an eye on your inbox!
(Credit: Gigabyte)
The company is marketing the product to AI researchers and software developers looking to run large language models (LLMs) at their desk, instead of paying a third-party server provider. The DGX Station can ensure the model runs privately while delivering fast performance, including running multiple AI-related tasks concurrently, Nvidia says. The same machine can also be shared over a local network as an “on-demand compute node for teams,” the company added.
NemoClaw: Nvidia Jumps on the OpenClaw Bandwagon
Despite the likely high price of the DGX Station, Nvidia sees a market for users who want to run AI models locally, pointing to the popularity of OpenClaw, an open-source autonomous AI agent that can run on a laptop or even a mini PC. Nvidia sees so much potential in OpenClaw that it announced its own contribution to the software, called NemoClaw.
Recommended by Our Editors
(Credit: Michael Kan)
On OpenClaw’s growing popularity, company CEO Jensen Huang even said: “This is as big of a deal as HTML, this is as big of a deal as Linux.”
NemoClaw has been designed to install OpenClaw alongside the company’s own AI programs, including Nvidia’s Nemotron models and the company’s newly-announced Nvidia Agent Toolkit. The result promises to bolster the intelligence and security of an OpenClaw installation, given that the AI agent software has been known to go rogue, such as deleting emails without permission or collecting sensitive data.
(Credit: Michael Kan)
NemoClaw can also run on all kinds of platforms, including laptops with Nvidia GPUs and on the DGX Spark and DGX Station. The company notes the Agent Tooklit “now includes Nvidia OpenShell—an open-source runtime that enforces policy-based security, network, and privacy guardrails that make autonomous agents, or claws, safer to deploy.”
About Our Expert
Michael Kan
Senior Reporter
Experience
I’ve been a journalist for over 15 years. I got my start as a schools and cities reporter in Kansas City and joined PCMag in 2017, where I cover satellite internet services, cybersecurity, PC hardware, and more. I’m currently based in San Francisco, but previously spent over five years in China, covering the country’s technology sector.
Since 2020, I’ve covered the launch and explosive growth of SpaceX’s Starlink satellite internet service, writing 600+ stories on availability and feature launches, but also the regulatory battles over the expansion of satellite constellations, fights with rival providers like AST SpaceMobile and Amazon, and the effort to expand into satellite-based mobile service. I’ve combed through FCC filings for the latest news and driven to remote corners of California to test Starlink’s cellular service.
I also cover cyber threats, from ransomware gangs to the emergence of AI-based malware. Earlier this year, the FTC forced Avast to pay consumers $16.5 million for secretly harvesting and selling their personal information to third-party clients, as revealed in my joint investigation with Motherboard.
I also cover the PC graphics card market. Pandemic-era shortages led me to camp out in front of a Best Buy to get an RTX 3000. I’m now following how President Trump’s tariffs will affect the industry. I’m always eager to learn more, so please jump in the comments with feedback and send me tips.
Read Full Bio
