--- title: NVIDIA DGX Spark · Ollama Blog | daily.dev description: NVIDIA DGX Spark, a desktop AI system powered by the GB10 Grace Blackwell Superchip delivering 1 petaFLOP of performance, now runs Ollama out-of-the-box... canonical: https://daily.dev/posts/nvidia-dgx-spark-ollama-blog-blsqbozff twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: NVIDIA DGX Spark · Ollama Blog | daily.dev og:description: NVIDIA DGX Spark, a desktop AI system powered by the GB10 Grace Blackwell Superchip delivering 1 petaFLOP of performance, now runs Ollama out-of-the-box... og:url: https://daily.dev/posts/nvidia-dgx-spark-ollama-blog-blsqbozff og:image: https://api.daily.dev/og/posts/bLsQbozfF.png og:image:alt: NVIDIA DGX Spark · Ollama Blog og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # NVIDIA DGX Spark · Ollama Blog **[Ollama](https://daily.dev/sources/ollama)** · 1 min read · 0 upvotes · 0 comments ## Summary NVIDIA DGX Spark, a desktop AI system powered by the GB10 Grace Blackwell Superchip delivering 1 petaFLOP of performance, now runs Ollama out-of-the-box through a partnership between the two companies. With 128GB of memory, it supports running large local models like Qwen, DeepSeek, Llama, Mistral, Gemma, and Gpt-oss, as well as custom or fine-tuned models. Ollama and NVIDIA are continuing to optimize performance across chat, document processing, code, and multimodal workloads. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What hardware does the NVIDIA DGX Spark use and how much memory does it have? The NVIDIA DGX Spark is powered by the GB10 Grace Blackwell Superchip, delivering 1 petaFLOP of performance and 128GB of memory. This memory capacity allows running large local language models such as Qwen, DeepSeek, Llama, Mistral, Gemma, and Gpt-oss, plus custom or fine-tuned models, directly on the device. _Developers evaluating local AI hardware can track new tools and integrations like this on daily.dev._ ## Similar posts on daily.dev - [NVIDIA DGX Spark: great hardware, early days for the ecosystem](https://daily.dev/posts/nvidia-dgx-spark-great-hardware-early-days-for-the-ecosystem-8avhsyx0d) · Simon Willison · 6 upvotes · 0 comments - [Nvidia sells tiny new computer that puts big AI on your desktop](https://daily.dev/posts/nvidia-sells-tiny-new-computer-that-puts-big-ai-on-your-desktop-dvq3my73q) · Ars Technica · 35 upvotes · 2 comments - [DGX Spark Nvidia's desktop supercomputer: first look](https://daily.dev/posts/dgx-spark-nvidia-s-desktop-supercomputer-first-look-ulgoxzbdw) · The Register · 0 upvotes · 0 comments - [NVIDIA DGX Spark: The developer’s personal AI supercomputer built on an Ubuntu base](https://daily.dev/posts/nvidia-dgx-spark-the-developer-s-personal-ai-supercomputer-built-on-an-ubuntu-base-udnb1yett) · Ubuntu · 2 upvotes · 0 comments - [Nvidia DGX Spark: The New Stack Developer’s Guide](https://daily.dev/posts/nvidia-dgx-spark-the-new-stack-developer-s-guide-xk9enevdy) · The New Stack · 2 upvotes · 0 comments --- Tags: [#nvidia](https://daily.dev/tags/nvidia), [#local-ai](https://daily.dev/tags/local-ai), [#ai-inference](https://daily.dev/tags/ai-inference), [#ollama](https://daily.dev/tags/ollama) [View this post on daily.dev](https://daily.dev/posts/nvidia-dgx-spark-ollama-blog-blsqbozff) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"NVIDIA DGX Spark · Ollama Blog","url":"https://daily.dev/posts/nvidia-dgx-spark-ollama-blog-blsqbozff","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/nvidia-dgx-spark-ollama-blog-blsqbozff"},"datePublished":"2026-08-23T12:22:19.455Z","dateModified":"2026-08-23T12:45:29.933Z","description":"NVIDIA DGX Spark, a desktop AI system powered by the GB10 Grace Blackwell Superchip delivering 1 petaFLOP of performance, now runs Ollama out-of-the-box...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Ollama","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Ollama","logo":"https://media.daily.dev/image/upload/s--dRYYkBCj--/f_auto,q_auto/v1787487632/logos/ollama-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/ollama"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/nvidia-dgx-spark-ollama-blog-blsqbozff","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"nvidia,local-ai,ai-inference,ollama","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ollama","item":"https://daily.dev/sources/ollama"},{"@type":"ListItem","position":3,"name":"NVIDIA DGX Spark · Ollama Blog"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/nvidia-dgx-spark-ollama-blog-blsqbozff#faq","mainEntity":[{"@type":"Question","name":"What hardware does the NVIDIA DGX Spark use and how much memory does it have?","acceptedAnswer":{"@type":"Answer","text":"The NVIDIA DGX Spark is powered by the GB10 Grace Blackwell Superchip, delivering 1 petaFLOP of performance and 128GB of memory. This memory capacity allows running large local language models such as Qwen, DeepSeek, Llama, Mistral, Gemma, and Gpt-oss, plus custom or fine-tuned models, directly on the device. Developers evaluating local AI hardware can track new tools and integrations like this on daily.dev."}}]} ```