DGX Spark packs 128GB of unified memory and is powerful enough to run models with 200 billion parameters locally.<\/p>\n
![\"\"](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2025\/10\/L1031489-retouch.jpg\")
<\/p>\n
Built for developers, researchers and creators who want supercomputer-class performance that\u2019s ready to grab and go.<\/p>\n
From robotics labs to creative studios, DGX Sparks are landing where ideas happen\u2026 putting petaflop AI within arm\u2019s reach of everyone.<\/p>\n
This blog will be updated as DGX Spark systems land from Ollama in Palo Alto to Arizona State\u2019s robotics lab, from Refik Anadol\u2019s studio to the hands of Jo Mardall at Zipline. Each delivery is a new chapter in the story of AI.<\/p>\n
What\u2019s Inside DGX Spark? A Supercomputer in the Palm of Your Hand<\/p>\n
![\"\"](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2025\/10\/1760428208_606_image4.jpg\")
<\/p>\n
It\u2019s the size of a piece of origami paper, and the thickness of a hardcover book. It acts like a rocket engine for AI.<\/p>\n
DGX Spark isn\u2019t just compact \u2014 it\u2019s dense with possibility. Inside its 1.2 kg chassis is a full-blown AI supercomputer built to take AI beyond the data center and into the hands of those who create.<\/p>\n
At its core:<\/p>\n
NVIDIA GB10 Grace Blackwell Superchip \u2014 delivering up to 1 petaflop of AI performance at FP4 precision.
\n128GB of unified CPU-GPU memory \u2014 so developers can prototype, fine-tune and run inference locally without bouncing between machines or cloud instances.
\nNVIDIA ConnectX networking for clustering and NVIDIA NVLink-C2C for 5x PCIe bandwidth.
\nNVMe storage for speed and HDMI out for visuals.<\/p>\n
And it\u2019s not just hardware. DGX Spark comes with the full NVIDIA AI software stack \u2014 frameworks, libraries, pretrained models and NVIDIA NIM microservices, ready to power workflows like:<\/p>\n
Customizing image-generation models such as FLUX.1
\nBuilding vision search and summarization agents with NVIDIA Cosmos
\nDeploying optimized chatbots using Qwen3<\/p>\n
This isn\u2019t a dev box. It\u2019s a launchpad\u2026 A petaflop of AI performance within arm\u2019s reach for developers, researchers and creators everywhere.<\/p>\n
Partners Power Up: DGX Spark Lands Beyond the Data Center<\/p>\n
![\"\"](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2025\/10\/1760428208_142_image2.jpg\")
\n<\/p>\n
From PC giants to AI pioneers, the diminutive DGX Spark is sure to start something big.\u00a0<\/p>\n
DGX Spark is already in the hands of innovators \u2014 from ISVs optimizing their tools to researchers pushing the boundaries of robotics, art and edge AI.
DGX Spark isn\u2019t just a breakthrough in size and performance\u2026 it\u2019s a platform built on collaboration. Acer, ASUS, Dell Technologies, GIGABYTE, HP, Lenovo and MSI are rolling out systems that put petaflop AI on your desk, transforming the desktop into an AI launchpad.
These partners deliver more than hardware. They deliver possibility \u2014 NVIDIA\u2019s full AI stack in a compact form factor that accelerates agentic and physical AI development everywhere ideas happen.<\/p>\n
And the rollout doesn\u2019t stop at OEMs. DGX Sparks are already lighting up the AI ecosystem. Some highlights:\u00a0<\/p>\n
Ollama in Palo Alto, rewriting how developers run large language models locally.
\nNYU Global Frontier Lab, where researchers prototype algorithms for privacy-sensitive applications.
\nZipline, pushing the boundaries of autonomous delivery.
\nArizona State University, running robotics simulations and vision models at the edge.
\nRefik Anadol\u2019s studio, blending art and AI with petaflop performance.<\/p>\n
From creative studios to robotics labs, DGX Sparks are landing where imagination meets engineering \u2014 taking AI beyond the data center and into the hands of those building what\u2019s next.<\/p>\n
DGX Spark will be generally available starting Wednesday, Oct. 15, on NVIDIA.com and through partners worldwide.<\/p>\n","protected":false},"excerpt":{"rendered":"The next AI revolution starts where rockets launch. NVIDIA DGX Spark\u2019s first stop: Starbase, Texas. NVIDIA founder and…\n","protected":false},"author":2,"featured_media":212206,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[256,254,255,64,63,105],"class_list":{"0":"post-212205","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-au","12":"tag-australia","13":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/212205","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/comments?post=212205"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/212205\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media\/212206"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media?parent=212205"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/categories?post=212205"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/tags?post=212205"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}