Nvidia opens orders for DGX Station, a desktop supercomputer running trillion-parameter AI models

Nvidia Opens Orders for DGX Station, Ready to Run Giant AI Models at Your Desk

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. 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. 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. 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. 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. 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. 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."

Nvidia's DGX Station is a desktop supercomputer that runs trillion-parameter AI models without the cloud

Nvidia on Monday unveiled a deskside supercomputer powerful enough to run AI models with up to one trillion parameters -- roughly the scale of GPT-4 -- without touching the cloud. The machine, called the DGX Station, packs 748 gigabytes of coherent memory and 20 petaflops of compute into a box that sits next to a monitor, and it may be the most significant personal computing product since the original Mac Pro convinced creative professionals to abandon workstations. The announcement, made at the company's annual GTC conference in San Jose, lands at a moment when the AI industry is grappling with a fundamental tension: the most powerful models in the world require enormous data center infrastructure, but the developers and enterprises building on those models increasingly want to keep their data, their agents, and their intellectual property local. The DGX Station is Nvidia's answer -- a six-figure machine that collapses the distance between AI's frontier and a single engineer's desk. What 20 petaflops on your desktop actually means The DGX Station is built around the new GB300 Grace Blackwell Ultra Desktop Superchip, which fuses a 72-core Grace CPU and a Blackwell Ultra GPU through Nvidia's NVLink-C2C interconnect. That link provides 1.8 terabytes per second of coherent bandwidth between the two processors -- seven times the speed of PCIe Gen 6 -- which means the CPU and GPU share a single, seamless pool of memory without the bottlenecks that typically cripple desktop AI work. Twenty petaflops -- 20 quadrillion operations per second -- would have ranked this machine among the world's top supercomputers less than a decade ago. The Summit system at Oak Ridge National Laboratory, which held the global No. 1 spot in 2018, delivered roughly ten times that performance but occupied a room the size of two basketball courts. Nvidia is packaging a meaningful fraction of that capability into something that plugs into a wall outlet. The 748 GB of unified memory is arguably the more important number. Trillion-parameter models are enormous neural networks that must be loaded entirely into memory to run. Without sufficient memory, no amount of processing speed matters -- the model simply won't fit. The DGX Station clears that bar, and it does so with a coherent architecture that eliminates the latency penalties of shuttling data between CPU and GPU memory pools. Always-on agents need always-on hardware Nvidia designed the DGX Station explicitly for what it sees as the next phase of AI: autonomous agents that reason, plan, write code, and execute tasks continuously -- not just systems that respond to prompts. Every major announcement at GTC 2026 reinforced this "agentic AI" thesis, and the DGX Station is where those agents are meant to be built and run. The key pairing is NemoClaw, a new open-source stack that Nvidia also announced Monday. NemoClaw bundles Nvidia's Nemotron open models with OpenShell, a secure runtime that enforces policy-based security, network, and privacy guardrails for autonomous agents. A single command installs the entire stack. Jensen Huang, Nvidia's founder and CEO, framed the combination in unmistakable terms, calling OpenClaw -- the broader agent platform NemoClaw supports -- "the operating system for personal AI" and comparing it directly to Mac and Windows. The argument is straightforward: cloud instances spin up and down on demand, but always-on agents need persistent compute, persistent memory, and persistent state. A machine under your desk, running 24/7 with local data and local models inside a security sandbox, is architecturally better suited to that workload than a rented GPU in someone else's data center. The DGX Station can operate as a personal supercomputer for a solo developer or as a shared compute node for teams, and it supports air-gapped configurations for classified or regulated environments where data can never leave the building. From desk prototype to data center production in zero rewrites One of the cleverest aspects of the DGX Station's design is what Nvidia calls architectural continuity. Applications built on the machine migrate seamlessly to the company's GB300 NVL72 data center systems -- 72-GPU racks designed for hyperscale AI factories -- without rearchitecting a single line of code. Nvidia is selling a vertically integrated pipeline: prototype at your desk, then scale to the cloud when you're ready. This matters because the biggest hidden cost in AI development today isn't compute -- it's the engineering time lost to rewriting code for different hardware configurations. A model fine-tuned on a local GPU cluster often requires substantial rework to deploy on cloud infrastructure with different memory architectures, networking stacks, and software dependencies. The DGX Station eliminates that friction by running the same NVIDIA AI software stack that powers every tier of Nvidia's infrastructure, from the DGX Spark to the Vera Rubin NVL72. Nvidia also expanded the DGX Spark, the Station's smaller sibling, with new clustering support. Up to four Spark units can now operate as a unified system with near-linear performance scaling -- a "desktop data center" that fits on a conference table without rack infrastructure or an IT ticket. For teams that need to fine-tune mid-size models or develop smaller-scale agents, clustered Sparks offer a credible departmental AI platform at a fraction of the Station's cost. The early buyers reveal where the market is heading The initial customer roster for DGX Station maps the industries where AI is transitioning fastest from experiment to daily operating tool. Snowflake is using the system to locally test its open-source Arctic training framework. EPRI, the Electric Power Research Institute, is advancing AI-powered weather forecasting to strengthen electrical grid reliability. Medivis is integrating vision language models into surgical workflows. Microsoft Research and Cornell have deployed the systems for hands-on AI training at scale. Systems are available to order now and will ship in the coming months from ASUS, Dell Technologies, GIGABYTE, MSI, and Supermicro, with HP joining later in the year. Nvidia hasn't disclosed pricing, but the GB300 components and the company's historical DGX pricing suggest a six-figure investment -- expensive by workstation standards, but remarkably cheap compared to the cloud GPU costs of running trillion-parameter inference at scale. The list of supported models underscores how open the AI ecosystem has become: developers can run and fine-tune OpenAI's gpt-oss-120b, Google Gemma 3, Qwen3, Mistral Large 3, DeepSeek V3.2, and Nvidia's own Nemotron models, among others. The DGX Station is model-agnostic by design -- a hardware Switzerland in an industry where model allegiances shift quarterly. Nvidia's real strategy: own every layer of the AI stack, from orbit to office The DGX Station didn't arrive in a vacuum. It was one piece of a sweeping set of GTC 2026 announcements that collectively map Nvidia's ambition to supply AI compute at literally every physical scale. At the top, Nvidia unveiled the Vera Rubin platform -- seven new chips in full production -- anchored by the Vera Rubin NVL72 rack, which integrates 72 next-generation Rubin GPUs and claims up to 10x higher inference throughput per watt compared to the current Blackwell generation. The Vera CPU, with 88 custom Olympus cores, targets the orchestration layer that agentic workloads increasingly demand. At the far frontier, Nvidia announced the Vera Rubin Space Module for orbital data centers, delivering 25x more AI compute for space-based inference than the H100. Between orbit and office, Nvidia revealed partnerships spanning Adobe for creative AI, automakers like BYD and Nissan for Level 4 autonomous vehicles, a coalition with Mistral AI and seven other labs to build open frontier models, and Dynamo 1.0, an open-source inference operating system already adopted by AWS, Azure, Google Cloud, and a roster of AI-native companies including Cursor and Perplexity. The pattern is unmistakable: Nvidia wants to be the computing platform -- hardware, software, and models -- for every AI workload, everywhere. The DGX Station is the piece that fills the gap between the cloud and the individual. The cloud isn't dead, but its monopoly on serious AI work is ending For the past several years, the default assumption in AI has been that serious work requires cloud GPU instances -- renting Nvidia hardware from AWS, Azure, or Google Cloud. That model works, but it carries real costs: data egress fees, latency, security exposure from sending proprietary data to third-party infrastructure, and the fundamental loss of control inherent in renting someone else's computer. The DGX Station doesn't kill the cloud -- Nvidia's data center business dwarfs its desktop revenue and is accelerating. But it creates a credible local alternative for an important and growing category of workloads. Training a frontier model from scratch still demands thousands of GPUs in a warehouse. Fine-tuning a trillion-parameter open model on proprietary data? Running inference for an internal agent that processes sensitive documents? Prototyping before committing to cloud spend? A machine under your desk starts to look like the rational choice. This is the strategic elegance of the product: it expands Nvidia's addressable market into personal AI infrastructure while reinforcing the cloud business, because everything built locally is designed to scale up to Nvidia's data center platforms. It's not cloud versus desk. It's cloud and desk, and Nvidia supplies both. A supercomputer on every desk -- and an agent that never sleeps on top of it The PC revolution's defining slogan was "a computer on every desk and in every home." Four decades later, Nvidia is updating the premise with an uncomfortable escalation. The DGX Station puts genuine supercomputing power -- the kind that ran national laboratories -- beside a keyboard, and NemoClaw puts an autonomous AI agent on top of it that runs around the clock, writing code, calling tools, and completing tasks while its owner sleeps. Whether that future is exhilarating or unsettling depends on your vantage point. But one thing is no longer debatable: the infrastructure required to build, run, and own frontier AI just moved from the server room to the desk drawer. And the company that sells nearly every serious AI chip on the planet just made sure it sells the desk drawer, too.

NVIDIA DGX Station GB300 Superchip Specifications and 748GB Unified Memory

NVIDIA has officially opened orders for its DGX Station, a desktop-class AI system built around the new GB300 Superchip. Announced during the company's GPU Technology Conference keynote, the system is positioned as a local AI development platform that brings data center-class performance into a workstation form factor. Compared to the previously released DGX Spark, the DGX Station represents a significant step forward, scaling performance from 1 PFLOP to up to 20 PFLOPS using FP4 precision with sparsity. At the heart of the DGX Station is NVIDIA's GB300 Superchip, which integrates a 72-core Grace CPU with a Blackwell Ultra GPU featuring 20,480 CUDA cores. This combination reflects the company's Grace-Blackwell architecture, designed to tightly couple CPU and GPU resources into a single coherent compute platform. The system runs NVIDIA's DGX software stack, enabling compatibility with enterprise AI workflows and allowing developers to move projects between local systems and large-scale data center deployments with minimal friction. A major highlight is the memory subsystem. The DGX Station features a total of 748GB of unified memory, consisting of 252GB of HBM3e on the GPU and 496GB of LPDDR5X attached to the CPU. Through NVLink-C2C interconnect, both processors can access the full memory pool, significantly reducing latency and eliminating traditional bottlenecks between system and graphics memory. This unified approach is particularly beneficial for large AI models, with NVIDIA indicating support for workloads approaching the trillion-parameter range depending on optimization. The platform also offers a range of expansion and connectivity options. The baseboard includes PCIe 5.0 slots for add-in cards, multiple M.2 interfaces for high-speed storage, and advanced networking capabilities such as dual 400 Gbit/s ConnectX-8 adapters alongside 10GbE connectivity. Unlike some previous DGX products, NVIDIA will not sell a Founders Edition system. Instead, it supplies the core motherboard with the integrated CPU and GPU, leaving partners such as ASUS, Dell, Gigabyte, MSI, and Supermicro to deliver complete workstation solutions. While pricing has not yet been disclosed, the DGX Station is clearly aimed at professionals working with large-scale AI models who require substantial local compute resources. Systems from OEM partners are expected to become available in the coming months.

NVIDIA DGX Station Upgraded With GB300 Blackwell Ultra Desktop Superchip: 748 GB Memory, 20 PFLOPs AI Compute & AI Ready

NVIDIA has introduced its updated DGX Station AI Supercomputer powered by the GB300 Blackwell Ultra Desktop Superchip. NVIDIA & Its Partners Introduce GB300 "Blackwell Ultra" Powered DGX Station: A Powerful AI Workstation With Meaty Specs Last year, NVIDIA introduced its DGX Station powered by the GB200 "Blackwell" Superchip, and also promised that a Blackwell Ultra variant was in the works. Now, at GTC 2026, NVIDIA is finally launching the GB300 "Blackwell Ultra" variant, featuring powerful specifications, and available in various options from its partners. The NVIDIA DGX Station is essentially an AI workstation that takes the revolutionary Blackwell Ultra Superchip and integrates it on a desktop-styled motherboard with various workstation-centric ports & components. This is more similar to a desktop PC that most of us are used to, though with some serious hardware integration. Starting with the specifications, the NVIDIA DGX Station for 2026 is equipped with a single NVIDIA GB200 "Blackwell Ultra" GPU. The NVIDIA Blackwell Ultra GB300 GPU packs a total of 160 SMs, each with a total of 128 CUDA cores, four 5th Gen Tensor cores with FP8, FP6, NVFP4 precision compute, 256 KB of Tensor memory or TMEM, and SFUs. This rounds up to a total of 20,480 CUDA cores and 640 Tensor cores, plus 40 MB of TMEM. Blackwell Ultra also brings a huge upgrade to memory, offering 252 GB of HBM3e capacities versus a max of 192 GB on the previous Blackwell GB200 solutions. The memory offers 7.1 TB/s bandwidth. The result is that NVIDIA's Blackwell Ultra GB300 platform is able to achieve a 50% increase in Dense Low Precision Compute output using the new NVFP4 standard. The new model delivers near FP8 accuracy, & the differences are often less than 1%. This also reduces the memory footprint by 1.8x versus FP8 and 3.5x versus FP16. As for the CPU, the DGX Station houses a single Grace chip with 72 cores based on the Neoverse V2 architecture. The system comes with 496 GB of LPDDR5X in addition to the HBM memory. The system memory offers 396 GB/s of bandwidth, and combined, you get 784 GB of memory. Both the CPU and GPU are connected using a 900 GB/s NVLink-C2C interconnect, and the system offers high-speed CX8 SuperNIC that delivers 800 Gb/s of networking speeds. The system comes with a 1600W TDP, features support for NVIDIA's latest RTX PRO Blackwell graphics cards, includes four M.2 Gen5 ports, four Ethernet ports (2 x 400 Gbs, 1 x 10 GbE, 1 x 1 GbE), a full PCIe Gen5 x16 slot, and two PCIe Gen5 x16 (x8 electrical) slots. The latest NVIDIA DGX Station is not only offered by NVIDIA but also by its partners, who have designed their own respective solutions. The following are the major GB300 DGX Station releases: None of the partners has the pricing listed, but we can expect the DGX Station GB300 to cost several thousand dollars based on the specs alone. These systems will be shipping this month. Follow Wccftech on Google to get more of our news coverage in your feeds.