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.

Feature	Hopper	Blackwell	Blackwell Ultra
Manufacturing process	TSMC 4N	TSMC 4NP	TSMC 4NP
Transistors	80B	208B	208B
Dies per GPU	1	2	2
NVFP4 dense | sparse performance	–	10 | 20 PetaFLOPS	15  | 20 PetaFLOPS
FP8 dense | sparse performance	2 | 4 PetaFLOPS	5 | 10 PetaFLOPS	5 | 10 PetaFLOPS
Attention acceleration (SFU EX2)	4.5 TeraExponentials/s	5 TeraExponentials/s	10.7 TeraExponentials/s
Max HBM capacity	80 GB HBM (H100)  141 GB HBM3E (H200)	192 GB HBM3E	288 GB HBM3E
Max HBM bandwidth	3.35 TB/s (H100) 4.8 TB/s (H200)	8 TB/s	8 TB/s
NVLink bandwidth	900 GB/s	1,800 GB/s	1,800 GB/s
Max power (TGP)	Up to 700W	Up to 1,200W	Up to 1,400W

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:

• ASUS ExpertCenter Pro ET900N G3
• Dell Pro Max With GB300
• Gigabyte W775-V10-L01
• MSI XpertStation WS300
• Supermicro Super AI Station GB300

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.