{"id":8874,"date":"2026-10-17T02:33:29","date_gmt":"2026-10-17T02:33:29","guid":{"rendered":"https:\/\/silvybrand.com\/?p=8874"},"modified":"2026-10-17T02:33:29","modified_gmt":"2026-10-17T02:33:29","slug":"nvidia-rtx-spark-windows-arm-laptops-asus-hp-lenovo-impressions","status":"publish","type":"post","link":"https:\/\/silvybrand.com\/?p=8874","title":{"rendered":"A week with RTX Spark: everything we\u2019ve learned using Nvidia\u2019s new laptops"},"content":{"rendered":"


\n<\/p>\n

\n
\n

Nvidia\u2019s RTX Spark N1X processor is finally here, and we\u2019ve been collectively testing a small fortune\u2019s worth of powerful laptops sporting this new \u201csuperchip.\u201d RTX Spark is designed to be a high-performing Arm-based SoC for laptops and small desktop computers, rivaling the best from Apple, Intel, AMD, and Qualcomm. It has loads of cores, Nvidia RTX Blackwell graphics, and enough power and unified memory to run sizable local AI models.<\/p>\n<\/div>\n

\n

The flagship placement is inside Microsoft\u2019s Surface Laptop Ultra with a staggering 128GB of unified memory, which our own Tom Warren fully reviewed<\/a>. Sean Hollister has been testing a 64GB version of the Asus ProArt P16, which I\u2019ve also been testing in its top-spec 128GB config. Since I\u2019m the most spoiled of the lot, I also have a 64GB Lenovo Yoga 9n 2-in-1 and a 32GB HP OmniBook Ultra in for testing.<\/p>\n<\/div>\n

\n

All of these laptops have the same N1X chip with 20 CPU cores and 6,144 GPU CUDA cores, and they\u2019re all wildly expensive \u2014 ranging from the HP OmniBook at $3,199.99 to the Asus ProArt\u2019s $6,999.99. There\u2019s an 18-core \/ 5,120 CUDA N1X chip in lower cost configs, but that only gets as cheap as $2,599.99 for a Surface Laptop Ultra<\/a> or a smaller Asus ProArt P14<\/a> with 24GB of RAM.<\/p>\n<\/div>\n

\n

These are big and expensive laptops built on new chips. They\u2019re meant for developers, coders, and content creators who might also want the ability to use local AI and even play games using the latest Nvidia tech like DLSS 5. There\u2019s a lot<\/em> to test, and we have not had a ton of time to test it all. So below you won\u2019t find an exhaustive scored review of any one laptop, but instead our impressions and thoughts from three writers using five laptops for a week.<\/p>\n<\/div>\n

\n

Is Nvidia\u2019s \u201csuperchip\u201d really all that super? Are Apple, Intel, AMD, and Qualcomm officially on notice? Have any of us gotten any sleep?<\/p>\n<\/div>\n

\n
\n
\n
\n
\n
\"A<\/a><\/div>\n<\/div>\n<\/div>\n

A laptop costing $7,000 better just work, and work well.<\/em><\/figcaption>Photo: Antonio G. Di Benedetto \/ The Verge<\/cite><\/p>\n<\/div>\n<\/div>\n<\/div>\n
\n

Antonio Di Benedetto:<\/strong> Windows on Arm is no longer a wholly subpar experience like it was a few years ago. Thanks in large part to the push around Qualcomm\u2019s Snapdragon X chips, lots of development has been put into native Arm-based apps for Windows. And many x86 apps work fine via Microsoft\u2019s Prism emulation layer.<\/p>\n<\/div>\n

\n

Adobe has had native Arm versions of Photoshop and Premiere for some time now, and even though my precious Lightroom Classic is still an x86-based app I don\u2019t notice any issues using it on Arm. At this point, you\u2019ve gotta be relying on specialized software that\u2019s exclusively x86 based for Windows on Arm to be a non-starter \u2014 or you want to freely play any games out there without any worry of incompatibilities.<\/p>\n<\/div>\n

\n

Sean Hollister:<\/strong> Every so often, there\u2019s that moment when an app takes longer to load than it should, and I wonder whether it\u2019ll load at all. Even then, it typically loads. Occasionally, it takes more than one try. My Evernote notes disappeared a few times one day when I alt-tabbed away, but a force refresh fixed that. And apps don\u2019t seem to respect my system preference for dark mode.<\/p>\n<\/div>\n

\n

But I largely agree with Antonio. I made an RTX Spark my daily driver, with all my typical work and personal apps \u2014 Signal, Discord, Audacity, CapCut and Evernote, Irfanview, Slack, ScreenToGif and more \u2014 and nothing has failed me so far. I never once needed to think whether I was running an Arm or an x86 app. The real hitches came with gaming and AI, as you\u2019ll read below.<\/p>\n<\/div>\n

\n

Tom Warren:<\/strong> I\u2019ve been using a Windows on Arm laptop with a Qualcomm chip daily for the past two years and things have improved to the point that I can\u2019t tell if an app is native or not anymore. That\u2019s the same story on the RTX Spark laptops, and I feel like Nvidia\u2019s entry into this category will only improve the story for creative apps and gaming.<\/p>\n<\/div>\n

\n
\n
\n
\n
\n
\"Gears<\/a><\/div>\n<\/div>\n<\/div>\n

Gears of War: E-Day running on the Surface Laptop Ultra during a Microsoft demo.<\/em><\/figcaption>Photo: Meron Menghistab<\/cite><\/p>\n<\/div>\n<\/div>\n<\/div>\n
\n

TW:<\/strong> Windows on Arm never looked like a serious gaming platform before now. While there still aren\u2019t many native Arm games, Nvidia\u2019s GPU helps bruteforce through the emulation layer. Your mileage in gaming is going to vary depending on the title, but for the most part I\u2019ve found that medium settings, running at 1440p and DLSS performance, will get you to a stable 60fps in most games.<\/p>\n<\/div>\n

\n

I mostly game on my desktop, where I\u2019m spoiled by using an RTX 5090 on a 32-inch 4K screen every day with maxed-out game settings, but I didn\u2019t mind the look of medium settings on a 15-inch display. I was able to run Black Myth: Wukong<\/em> at 70fps on average at native resolution (3270 x 2180) with medium settings and DLSS performance mode enabled. I ran the same medium settings and DLSS performance in Cyberpunk 2077<\/em> and averaged 66fps, and Forza Horizon 6<\/em> managed an average of 57fps.<\/p>\n<\/div>\n

\n

In some titles you may need to drop the resolution or settings lower, though. This definitely isn\u2019t as good as a dedicated gaming laptop, but for something that\u2019s roughly on the level of a MacBook Pro it\u2019s more than good enough for gaming on the go.<\/p>\n<\/div>\n

\n

SH:<\/strong> Like Tom says, the GPU power is there \u2014 but the CPU might hold back some of your games. I had plenty of power for a smooth 60fps in Returnal<\/em> (at 1440p with high settings), Expedition 33<\/em> (at a DLSS \u201cPerformance\u201d upscaled 1200p with high settings), Jedi Survivor<\/em> (DLSS \u201cPerformance\u201d upscaled 1200p with medium settings), and Shadow of the Tomb Raider<\/em> (at native 1800p and highest spec).<\/p>\n<\/div>\n

\n

But when I fired up Helldivers 2<\/em>, even dipping down to a DLSS-upscaled 1080p was no guarantee of 60fps in the highest difficulty missions. There are just too many enemies on screen for the Spark to keep up. Star Wars Zero Company<\/em> is even more CPU-bound<\/a> \u2014<\/em> the Spark didn\u2019t care whether I was maximizing or minimizing the graphics and screen resolution. No matter what I tried, I typically saw my framerate capped between 37fps and 39fps in battle.<\/p>\n<\/div>\n

\n

Even ancient and low-powered games can have quirks. I tried the 2003 title Max Payne 2<\/em> and saw situations where framerate dipped to 50fps. I even saw a few hitches in the excellent UFO 50<\/em>, a collection of 2D games, though a couple other 2D games ran great.<\/p>\n<\/div>\n

\n

I\u2019m also not sure if RTX Spark is suitable for VR yet. The excellent Titanfall 2<\/em> VR mod<\/a> worked, and it seemed to run fine at first, but lost a little stability after a few minutes. That could be my Wi-Fi, because the driver for Valve\u2019s Steam Frame<\/a> wireless adapter wouldn\u2019t install on the Spark. Neither did Steam\u2019s streaming audio solution, so the audio came out of the Nvidia laptop instead of the headset.<\/p>\n<\/div>\n

\n

Just so we\u2019re clear, all of this is assuming you want a laptop maxing out its fans and positively dumping heat on your desk or lap. That\u2019s not unusual for thin gaming notebooks, but it\u2019s way<\/em> louder and hotter than a good desktop or handheld.<\/p>\n<\/div>\n

\n
\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

<\/th>\n

\n

2560×1600<\/h3>\n<\/th>\n

\n

2560×1600<\/h3>\n<\/th>\n

\n

2560×1600<\/h3>\n<\/th>\n

\n

2560×1600<\/h3>\n<\/th>\n<\/tr>\n<\/thead>\n

\nAsus ProArt P16 RTX Spark (20-core, 6144 CUDA, 128GB RAM)<\/td>\nHP OmniBook Ultra RTX Spark (20-core, 6144 CUDA, 32GB RAM)<\/td>\nFramework Laptop 16 5070 (2025, 8GB VRAM)<\/td>\nMacBook Pro M5 Max<\/td>\n<\/tr>\n
Black Myth: Wukong TSR<\/td>\n27<\/td>\n27<\/td>\n28<\/td>\nNot compatible<\/td>\n<\/tr>\n
Black Myth: Wukong DLSS<\/td>\n41<\/td>\n44<\/td>\n45<\/td>\nNot compatible<\/td>\n<\/tr>\n
Black Myth: Wukong DLSS FG<\/td>\n53<\/td>\n59<\/td>\n71<\/td>\nNot compatible<\/td>\n<\/tr>\n
Cyberpunk 2077 Ultra<\/td>\n41<\/td>\n46<\/td>\n57<\/td>\n56<\/td>\n<\/tr>\n
Cyberpunk 2077 Ultra RT & DLSS quality<\/td>\n30<\/td>\n35<\/td>\n44<\/td>\n42 (MetalFX Quality)<\/td>\n<\/tr>\n
Cyberpunk 2077 Ultra RT & DLSS Frame Gen x2<\/td>\n53<\/td>\n56<\/td>\n68<\/td>\n75 (MetalFX Quality, FSR 3.1 FG)<\/td>\n<\/tr>\n
Cyberpunk 2077 Ultra RT & DLSS Frame Gen x4<\/td>\n92<\/td>\n103<\/td>\nNot tested<\/td>\nNot compatible<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n

Average FPS results in gaming benchmarks we ran on the Asus ProArt P16 and HP OmniBook Ultra, against an RTX 5070 Laptop GPU and M5 Max MacBook Pro.<\/em><\/figcaption><\/p>\n<\/div>\n<\/div>\n<\/div>\n
\n

AD:<\/strong> I\u2019ve wanted a MacBook Pro-like laptop with full PC gaming chops for as long as I can remember, so I was hyped for these laptops to deliver the goods in graphics. The first night, I set up the Asus ProArt P16, with all 128GB of its ridiculously large pool of memory, and when I booted up Big Walk<\/em> for my planned online evening with some friends my first thought was, \u201cWell, that looks okay. I guess.\u201d I know Big Walk<\/em> isn\u2019t some triple-A graphical titan, but it has some fairly demanding graphics for the \u201cfriend slop<\/a>\u201d genre. I expected the N1X to max it out, or at least get close, but not really.<\/p>\n<\/div>\n

\n

I had to bump the P16\u2019s 4K display down to 2560 x 1600, and instead of Big Walk\u2019s<\/em> Highest or Very high graphics presets, I brought it down to High to maintain a decently solid 60-ish fps. Does any of that really matter for this silly co-op game about solving puzzles with your buddies? Of course not. It looked fine, after all. But it was a sobering reminder that this \u201csuperchip\u201d is no graphical magician.<\/p>\n<\/div>\n

\n

As Tom and Sean point out, RTX Spark can do some decent gaming, but temper your expectations for medium or even low settings in some cases, and be ready to rely on DLSS and frame gen. There\u2019s no denying that cheaper desktops and even laptops with discrete Nvidia graphics cards can easily beat out an N1X. Nvidia claims it\u2019s like having an RTX 5070 Laptop GPU in an SoC, but in my testing it was somewhere between that and an RTX 5060 Laptop GPU \u2014 not a slouch, for sure, but if you\u2019re a gamer first your money goes much further with traditional Nvidia graphics cards.<\/p>\n<\/div>\n

\n

How\u2019s the battery life?<\/h2>\n<\/p>\n<\/div>\n
\n
\n
\n
\n
\n
\"Sadly,<\/a><\/div>\n<\/div>\n<\/div>\n

Sadly, only Microsoft\u2019s Surface Laptop Ultra has that slick magnetic USB-C charging.<\/em><\/figcaption>Photo: Meron Menghistab<\/cite><\/p>\n<\/div>\n<\/div>\n<\/div>\n
\n

SH:<\/strong> Nvidia\u2019s partners saw fit to equip their first wave of RTX Spark laptops with some of the biggest batteries you can bring on an airplane with no questions asked \u2014 but even with a 99.9 watt-hour pack like the one in my Asus ProArt P16, these laptops won\u2019t be winning awards for longevity. While Tom and Antonio spent their days testing every use case under the sun, I made the P16 my daily driver for normal<\/em> work while watching the battery meter like a hawk. That mostly means writing stories in a web browser, and it\u2019s not quite lasting the day.<\/p>\n<\/div>\n

\n

My best run was 5 hours and 40 minutes of real-world work at 50 percent brightness, including an hour-long video call with Tom and Antonio to strategize our RTX Spark coverage plan. The next day, I got only about 5 hours from a full charge because I spent two of them editing this video<\/a> in Capcut. The third time I drained the battery, it took 5 hours, too.<\/p>\n<\/div>\n

\n

With web work, I\u2019m typically seeing 13-17 watt battery drain on the laptop\u2019s default settings, but that climbs to 20-30 watts with light video work, up to 50 watts during the (brief) Capcut video export, and I made it jump all the way to 120 watts playing Indiana Jones and the Great Circle<\/em>. The battery couldn\u2019t keep feeding at that rate \u2014 it slowly went down, and at 30 percent charge I saw a big performance hit as it dropped dramatically to 60 watts.<\/p>\n<\/div>\n

\n

The good news is the Asus charges fast<\/em> from a 140W USB-C PD power source. It took 20 minutes to go from dead to 50 percent battery, another 15 minutes to get to 70 percent, and a total of 1 hour, 15 minutes to reach 95 percent charge.<\/p>\n<\/div>\n

\n

AD:<\/strong> I\u2019ve had to run lots of benchmarks while plugged in, so I haven\u2019t been able to spend as much time testing battery life as I\u2019d normally like. Anecdotally, in lots of fits and starts, battery life seems solid. As Sean saw, you\u2019re unlikely to get through a full eight hour work day unless you\u2019re going out of your way to be efficient. And if you fire up anything heavy, like a local AI model (more on that in a minute), you won\u2019t even make it to lunch. I\u2019ll eventually do more thorough battery testing as I continue using these laptops, including our usual rundown tests for a bit of 1:1 comparisons.<\/p>\n<\/div>\n

\n

Does local AI seem useful?<\/h2>\n<\/p>\n<\/div>\n
\n
\n
\n
\n
\n
\"A<\/a><\/div>\n<\/div>\n<\/div>\n

A local AI model running on a Surface Laptop Ultra.<\/em><\/figcaption>Photo: Meron Menghistab<\/cite><\/p>\n<\/div>\n<\/div>\n<\/div>\n
\n

TW:<\/strong> Not yet. It all feels like a beta aimed at developers right now: from the install experience of AI agents flashing up command prompts and Visual Studio, to the fans blasting away for the most basic of queries.<\/p>\n<\/div>\n

\n

I struggled to come up with many compelling use cases for the power of these chips for local AI work. A lot of tasks could simply be done far more quickly and without the laptop fans spinning up by using a free cloud model. The power here is really in leaving the agent running at full throttle to build something overnight, running tasks that developers would favor.<\/p>\n<\/div>\n

\n

It\u2019s also nice to have this all on a local device, without having to share emails and files with a cloud service and worry about the privacy aspects. Still, I would regularly close OpenClaw or Hermes and not let them run in the background all day, especially if I had given them permissions to access local files. I\u2019m just not ready to trust AI fully, local or not.<\/p>\n<\/div>\n

\n

Microsoft and Nvidia both envision a future where AI agents automate things on your PC, but I\u2019m still not fully convinced. While there are some mundane tasks I could certainly automate, I like using my PC to edit photos or videos, write, and play games. I don\u2019t want to sit there and watch a robot do all of that for me. That\u2019s part of the joy of computing to me.<\/p>\n<\/div>\n

\n

SH:<\/strong> I walked out of Nvidia\u2019s Editor\u2019s Day<\/a> thinking I might finally have a reason to fire up local AI. I asked Hermes, running Qwen3.8-27B, to build me a daily news briefing much like the one in Nvidia\u2019s on-stage demo. It took 10 minutes, and 10 percent of my entire 99.9 watt-hour battery, to finally produce a list of stories that took the cloud-based Claude (Opus 5.5) half as long \u2014 while utterly monopolizing my GPU and dramatically heating up the Spark laptop. The laptop stayed hot and a little sluggish as long as I kept Hermes open.<\/p>\n<\/div>\n

\n

Claude also produced better results, with more detail and better sourcing. I guess I got the local AI tokens for \u201cfree,\u201d I wouldn\u2019t trust Claude with my email, and I probably could have used a smaller, lighter model. But I went with what the program recommended, and that was the result. I tried a clean reinstall of Hermes to make sure it wasn\u2019t a misconfiguration, but this time, the prompt took even longer and used 60<\/em> percent of my battery. Ouch.<\/p>\n<\/div>\n

\n
\n
\n
\n
\n
\"<em>Seems<\/a><\/div>\n
\"<em>Not<\/a><\/div>\n