A Petaflop in Your Backpack: RTX Spark and the Shift to Local AI
Alt headlines to A/B test: The Cloud-Bill Killer? RTX Spark Puts a Full Petaflop of AI on Your Lap Local AI Just Got Serious: 128 GB and a Petaflop, Unplugged Stop Renting GPUs. RTX Spark Brings Data-Center AI to Your Desk — and Your Bag For the last few years, doing real AI work meant one thing: renting someone else's hardware. Spin up an instance, watch the meter run, ship your data to a server you don't control, and hope the latency cooperates. RTX Spark is a bet that the next era looks different — that the most interesting AI will run where you are, on hardware you own. And the spec sheet backs up the ambition. The numbers that matter to builders Up to 1 petaflop of FP4 AI performance Up to 128 GB of unified memory Up to 6,144 cores of Blackwell RTX GPU Up to 20 cores of ultra-efficient CPU If you build with AI, two of these should stop your scroll. A full petaflop of FP4 is the kind of throughput that turns "let it run overnight" into "let it run over lunch." And 128 GB of unified memory is the unlock almost no portable machine offers: CPU and GPU share one giant pool, so you can hold large models and big context entirely in memory — no swapping, no artificial caps on the size of what you load. The workloads that used to demand a rack now fit in a bag. Why this is a big deal for AI work CUDA runs natively. The platform that accelerates the world's AI runs at full speed on RTX Spark — meaning the frameworks, libraries, and agentic stacks you already use just work. No exotic ports, no "supported soon." That changes the day-to-day in three concrete ways: Fewer cloud bills. Prototype, fine-tune, and run inference locally instead of burning credits every time you iterate. Your data stays yours. Sensitive datasets never leave the device — a quiet superpower for anyone working under compliance or NDA. Build agents anywhere. A genuinely portable petaflop means you can develop and test agentic workflows on a train, in a client's office, or off the grid entirely. For the wave of teams building agents and AI products right now, "local-first" stops being a compromise and starts being an advantage. A petaflop that doesn't need a power brick Here's the part that makes the rest believable: RTX Spark is built around the most power-efficient RTX chip ever made. That efficiency is why a petaflop can live in a slim chassis and last all day. Performance you can only use while tethered to a wall isn't really portable performance — and that's the trap RTX Spark is designed to avoid. When the work is done It's not all inference and fine-tuning. The same silicon makes RTX Spark a creator's machine — hundreds of creative apps and AI tools accelerated by RTX and NVIDIA Studio — and a genuine gaming rig after hours, with ray tracing, the full DLSS suite, NVIDIA Reflex, and G-SYNC. One device, three lives. The takeaway The story of AI has been a story of renting access to power. RTX Spark points at a different future: owning it, carrying it, and pointing it at whatever you're building — without the meter running. So here's the real question If you had a portable petaflop with 128 GB of unified memory, what's the first thing you'd run on it — a local LLM, an agent swarm, your own fine-tune? Drop it in the comments. I'm genuinely curious what this community would build first.
5 AI Predictions Every Infrastructure Leader Needs to Know in 2026
January 22 | Register Now! In 2026, AI moves from experimentation to execution—and infrastructure leaders are in the driver's seat. Organizations that build the right data foundations now will be the ones turning AI into a true competitive advantage. Join us as we explore five trends shaping the future of AI infrastructure, from unlocking the value of your data to architecting for production-scale AI workloads. Walk away with a clear roadmap for positioning your infrastructure as the engine that powers your organization's AI ambitions. In this webinar, you'll learn: How to get your data ready for AI All about the NVIDIA AI Factory and Data Platform What it takes to scale AI from pilot to production Practical ways to bring AI into your organization Register Now!Introducing Pure Storage Data Stream for AI Data Readiness
Cool news to share from Pure's presence at NVIDIA GTC this week - the announcement of a new solution - Pure Storage Data Stream - that accelerates data readiness by automating and speeding up the ingestion, transformation, and optimization of data for enterprise AI pipelines. "Data Stream is a GPU-centric AI-powered, integrated hardware and software stack built for data readiness to automate and accelerate the ingestion, transformation, and optimization of data for enterprise AI pipelines. It is a core component of Pure Storage Data Platform built for enterprise inference use cases, using the NVIDIA AI Data Platform reference design, a comprehensive, single-appliance, jointly engineered infrastructure stack tailored for AI inference via generative AI applications." Register for a preview here: https://www.pure.ai/data-stream.html Blog announcement: https://blog.purestorage.com/products/driving-the-future-of-ai-data-readiness-pure-storage-data-stream/Accelerate Breakout Replay: Feeding the Beast: Designing Storage Architectures to Optimize GPU Utilization
Explore how to build AI-ready storage with high-throughput, low-latency architectures to keep GPUs fed while eliminating I/O bottlenecks. Speakers: Kevin Parker Ed Hsu Mike Webb, Silicon Labs https://www.purestorage.com/video/webinars/designing-storage-architectures-to-optimize-gpu-utilization/6375343080112.htmlAccelerate Breakout Replay: Panel Discussion - How to Make AI Succeed in Your Organization
Hear from experts on how to build scalable AI platforms with Pure Storage & Portworx®—balancing data, infrastructure, and performance. Speakers: Nathan Wood Victor Olmedo Tony Paikaday, NVIDIA https://www.purestorage.com/video/webinars/how-to-make-ai-succeed-panel/6375339058112.htmlHave you implemented AI solutions using FlashStack?
If so, how has your experience been? If not, do you have any questions? A joint solution by Pure Storage, Cisco, and NVIDIA simplifies the complexities of AI with high performance, validated designs, and enhanced scalability. It's designed to meet the demands of AI workloads with ease. Read all about it!How to install Portworx with OpenShift using Operator
Just received this from my partner jerewis ---------------------------------- Bruce, Did a POC with customer last two days. Ran into typical issues with RedHat CEPH and customer needs HA storage and DR. I want to stage up a POC… but quickly get them up and working so send over deployment guide / notes from my OCP 4.10 install which is same as theirs.. But base operator runs into error now on install. https://docs.portworx.com/portworx-install-with-kubernetes/openshift/operator/|Portworx Operator Step 1: Install Operator based deployment at je (https://console-openshift-console.apps.os01.penguinpages.local/static/operator-hub-chunk-2eb5d8d8564dbeb077bc.min.js68826) at div at div at div at div at Ce (https://console-openshift-console.apps.os01.penguinpages.local/static/operator-hub-chunk-2eb5d8d8564dbeb077bc.min.js69846) at o (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js235714) at t (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js58473) at t (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js60518) at Suspense at div at _ (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js160553) at N (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js161001) at div at https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js797038 at p.memo.t.children.e.children.t.reduxes.e.reduxes.t.reduxes.every.reduxID (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js533369) at S (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js81479) at <anonymous> (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js534723) at S (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js81479) at https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js999429 at o (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js235714) at DetailsPage at Me (https://console-openshift-console.apps.os01.penguinpages.local/static/operator-hub-chunk-2eb5d8d8564dbeb077bc.min.js75884) at s (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js297536) at https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js623539 at S (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js81479) at t (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js58473) at t (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js60518) at Suspense at section at f (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js43758) at div at div at t.a (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1629287) at div at div at c (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js501467) at d (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js80399) at div at d (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js603442) at l (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1280462) at https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js551440 at S (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js81479) at main at div at O (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js741428) at div at div at c (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js167229) at div at div at c (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js501467) at d (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js80399) at div at d (https://console-openshift-console.apps.os01.penguinpages.local/static/vendor-patternfly-core-chunk-0d6fac2ae3356385121e.min.js603442) at hn (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js181594) at t.a (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1122640) at t.default (https://console-openshift-console.apps.os01.penguinpages.local/static/quick-start-chunk-5dee0a535cd19ebed06e.min.js1223) at s (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js297536) at t.a (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1702480) at Q (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1721987) at et (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js143623) at Q (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1721987) at Q (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1721987) at t.a (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1698183) at c (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1695586) at t.a (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1697994) at J (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1722117) at https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1724876 at r (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js119264) at t (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js58473) at t (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js60518) at t (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js55078) at X (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js1725222) at t.a (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js923308) at t.a (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js865474) at t.a (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js413803) at Suspense ```TypeError: Cannot read properties of undefined (reading 'apiGroup') at a (https://console-openshift-console.apps.os01.penguinpages.local/static/main-chunk-5cff3a21ac5fb65a3b41.min.js185039) at je (https://console-openshift-console.apps.os01.penguinpages.local/static/operator-hub-chunk-2eb5d8d8564dbeb077bc.min.js69052) at na (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js58879) at Hs (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js111315) at xc (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js98327) at Cc (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js98255) at _c (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js98118) at pc (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js95105) at https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js44774 at t.unstable_runWithPriority (https://console-openshift-console.apps.os01.penguinpages.local/static/vendors~main-chunk-41ccebee3877b1a26e8b.min.js3768)``` This is base operator install … so not much help here on debug at this early of a stage. ------------------------------------------------------------------ is there someone that can help out on this? Portworx Documentation How to install Portworx with OpenShift using Operator
