NVIDIA DGX Spark and DGX Station Personal AI Computers

Today, NVIDIA launched the NVIDIA DGX personal AI supercomputers, which are driven by the NVIDIA Grace Blackwell platform.

[{"selector":"#anim-8ba6f8b3-d4c9-4c8c-87e7-5a3677279d93","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}]

These models can be deployed on NVIDIA DGX Cloud or any other accelerated cloud or data centre infrastructure, or users can run them locally

[{"selector":"#anim-fe9fa207-b7c4-4ec8-b448-e47d979af93b","keyframes":[{"offset":0,"transform":"translate3d(0, -377.21914%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.29,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.45,"transform":"translate3d(0, -106.074022168%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.61,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.71,"transform":"translate3d(0, -36.062149784%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.8,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.85,"transform":"translate3d(0, -13.542167126%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.92,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.96,"transform":"translate3d(0, -5.884618583999999%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":1,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"}],"delay":0,"duration":600,"fill":"both"}]

ASUS, Dell, HP Inc., and Lenovo are among the international system manufacturers working on DGX Spark and DGX Station

[{"selector":"#anim-366f4666-1737-490e-a2d2-c03f4b3cd2d3","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}]

DGX Spark, the world's smallest AI supercomputer, lets millions of researchers, data scientists, robotics developers, and students advance generative and physical AI

[{"selector":"#anim-2b3b7fa3-9c0b-4f5d-b5bd-b340e496b1da","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.2, 0.6, 0.0, 1)","fill":"both"}] [{"selector":"#anim-73eaa12d-f134-469f-8b47-b507bde1d990","keyframes":{"transform":["translate3d(0px, -294.3647%, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.2, 0.6, 0.0, 1)","fill":"both"}]

GB10's NVIDIA Blackwell GPU with fifth-generation Tensor Cores and FP4 support can calculate 1,000 trillion AI operations per second

[{"selector":"#anim-af6255a3-e88b-44d1-9945-287d78434a83","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.2, 0.6, 0.0, 1)","fill":"both"}] [{"selector":"#anim-bba5ba43-fa7b-4674-9581-0633177dd47a","keyframes":{"transform":["translate3d(0px, 131.96773%, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.2, 0.6, 0.0, 1)","fill":"both"}]

GB10 Superchip offers a CPU+GPU-coherent memory model with five times the bandwidth of fifth-generation PCIe to NVIDIA NVLink-C2C connection technology

[{"selector":"#anim-daa9468c-b264-49ae-ba24-3f1c3aa10462","keyframes":{"transform":["scale(1)","scale(1.5)","scale(0.95)","scale(1)"],"offset":[0,0.33,0.66,1]},"delay":0,"duration":1450,"easing":"ease-in-out","fill":"both","iterations":1}]

DGX Station, the first desktop with the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip, speeds up

[{"selector":"#anim-08ebfbc7-ed65-4da7-84f5-d69289a71dfc","keyframes":{"transform":["translate3d(-115.2381%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-fca4442d-da7b-493c-86c6-a306411b6986","keyframes":{"transform":["rotateZ(-180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}]

NVIDIA ConnectX-8 SuperNIC, designed to boost hyperscale AI computing workloads, is another aspect of DGX Station

[{"selector":"#anim-edda8ff5-0e5f-4427-93f1-c32629267014","keyframes":{"transform":["translate3d(115.53399%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-52544acb-54c6-4649-aab7-bf88d6c7bf49","keyframes":{"transform":["rotateZ(180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}]

ConnectX-8 SuperNIC provides incredibly fast and efficient network access with capability for networking at up to 800Gb/s

[{"selector":"#anim-5a55be8d-fdac-488a-9b38-df8a5f143bd8","keyframes":{"transform":["rotate(-540deg) scale(0.1)","none"],"opacity":[0,1]},"delay":0,"duration":1000,"fill":"both","iterations":1}]

NVIDIA GB10 Grace Blackwell Superchip, offers 1000 AI TOPS of AI performance in a small, power-efficient package

[{"selector":"#anim-47ee7ed3-0e6e-495a-b475-09e52094962b","keyframes":{"transform":["translate3d(-115.2381%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-b5278b2e-ccb3-4932-9083-5bdb8ce605ac","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-f61fcc35-5d2f-462f-86d4-08a142ed7678","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

NVIDIA DGX Spark lets developers design, test, and validate AI models and AI-enhanced apps and solutions using the NVIDIA AI software stack

[{"selector":"#anim-0c71edd0-b714-4a1d-bbb4-67324e26646d","keyframes":{"transform":["translate3d(115.55555%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-9c017f34-cbc1-40f3-a414-bc6bd5aba1e1","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-02aae002-ebec-4efe-9d10-48c6d6b7c658","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

Developers may quickly create edge applications by utilising the capabilities of NVIDIA DGX Spark to these frameworks and tools

[{"selector":"#anim-8e719c79-943f-47fb-8ee4-8f3055a9a39c","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-7f897d09-2efc-4e4c-9906-fa6be794e349","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]

DGX Station A100 320G costs $149,000, while the 160G variant costs $99,000 Read more on Govindhtech.com

[{"selector":"#anim-ec18c3af-402a-4f27-beed-44b8607cbfd1","keyframes":{"transform":["translate3d(120.13201%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-7cd587c7-75ba-4c1e-af44-a2cd21c23d45","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-2e320a54-4e5f-4e7b-bf76-86d609fbcdd6","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]