When will this system be available, and how much will it cost?

NVIDIA states RTX Spark systems arrive beginning Fall 2026 in select regions, with ASUS and MSI systems first and Acer and GIGABYTE following. No official pricing has been announced by NVIDIA or any brand, in any market. Figures circulating in the technology press are analyst estimates rather than confirmed prices, so EMARQUE does not quote them.For Malaysia, the ASUS ProArt P16 and P14 have been reported for Q3 2026 availability by Malaysian press; no other brand has given a Malaysia date. Contact EMARQUE and we will let you know as soon as local availability and pricing are confirmed: WhatsApp 012 627 2280 or business@emarque.co.

Will my existing Windows applications run on RTX Spark?

RTX Spark uses an Arm-based NVIDIA Grace CPU, so Windows runs x86 applications through Prism emulation, which Microsoft states is tuned for the microarchitecture of RTX Spark.NVIDIA published its first GeForce driver for Windows on Arm in July 2026, alongside the CUDA Toolkit 13.4 developer preview, which adds native Windows Arm64 development for RTX Spark. Arm64EC lets a native Arm application keep using existing x64 libraries. NVIDIA is also partnering with Adobe to rearchitect Premiere and Photoshop for RTX Spark, work that is in progress rather than finished.Applications compiled natively for Arm64 will run best, and most mainstream x86 software runs under emulation. If your work depends on plugin-heavy professional software, confirm its Arm64 support before ordering. EMARQUE can check compatibility for your workflow before you commit.

How is RTX Spark different from NVIDIA DGX Spark?

They are different products with similar names. RTX Spark is a Windows AI PC platform built on the RTX Spark Superchip, for laptops and compact desktops. DGX Spark is a Linux desktop AI supercomputer built on the GB10 Grace Blackwell Superchip, running NVIDIA DGX OS.Different chip, different operating system, different purpose. If you need a local AI machine today rather than in Fall 2026, NVIDIA DGX Spark is available now from EMARQUE. For the full platform FAQ, see the NVIDIA RTX Spark lineup.

1 1

COMING SOONExpected Fall 2026

HP OmniBook X 14 NVIDIA RTX Spark AI Laptop

Coming Soon. Shipping worldwide from October 2026. Malaysia availability to be confirmed.

13.53mm at the rear, and HP says that makes it the thinnest

HP puts the OmniBook X 14 at 13.53mm measured near the back edge, and calls the RTX Spark OmniBooks the world's thinnest RTX Spark machines. Both figures come from HP's own Computex release. Getting there meant moving the thermal architecture behind the hinge, so the hot air leaves at the back rather than through the deck while the NVIDIA RTX Spark™ Superchip is working. Beyond the dimensions, HP has not yet published a specification sheet for this model.

13.53mm rear height: HP-published, and the thinnest of the two RTX Spark OmniBooks. Its 16-inch sibling measures 15.73mm.
Rear thermal architecture: cooling exits behind the hinge, keeping sustained AI work away from the keyboard and palm rest.
Up to 128GB unified memory on the RTX Spark platform, shared between CPU and GPU.
Reported at HP's briefing, not yet on an HP spec page: a 14-inch 3K OLED at 2880 x 1800 with VESA DisplayHDR True Black 1000, an 80Wh battery rated to 15 hours, a 140W USB-C GaN adapter reaching 50% in about 30 minutes, 1.71kg, and 32GB, 64GB or 128GB of LPDDR5X-9400 with 1TB or 2TB of SSD.

HP OmniBook X 14 specifications

Platform: NVIDIA RTX Spark Superchip, Blackwell RTX GPU with Arm-based NVIDIA Grace CPU
GPU: 6,144-core Blackwell RTX, 5th-gen Tensor Cores at FP4
CPU: 20-core NVIDIA Grace
AI performance: up to 1 petaflop FP4
Rear height: 13.53mm, published by HP
Display, reported: 14-inch 3K 2880 x 1800 OLED, up to 120Hz, VESA DisplayHDR True Black 1000
Unified memory, reported: 32GB, 64GB or 128GB LPDDR5X-9400
Storage, reported: 1TB or 2TB SSD
Battery, reported: 80Wh, up to 15 hours, 140W USB-C GaN charging
Weight, reported: 1.71kg
Cooling: rear thermal architecture
Operating system: Windows
Availability: shipping worldwide from October 2026, Malaysia to be confirmed

Its 16-inch sibling, the OmniBook Ultra 16, trades 2.2mm of thickness for a larger battery and quad speakers. The ASUS ProArt P14 is the other 14-inch in the range, and ASUS has published its full specification. The rest are on our NVIDIA RTX Spark page.

HP has published dimensions and the RTX Spark platform for this model. Items marked reported come from HP's Computex briefing as covered by the technology press, and we will replace them with HP's own figures when HP publishes a specification sheet. Pricing and Malaysia availability are subject to official NVIDIA and HP confirmation.

Important — pre-launch information

Specifications, pricing and Malaysia availability for NVIDIA RTX Spark products are subject to official confirmation by NVIDIA and the respective OEM. Content on this page reflects information published at announcement. EMARQUE will update each product page as official Malaysia availability and pricing are confirmed.

View the full NVIDIA RTX Spark lineup → · Available now: NVIDIA DGX Spark →

View full details

Inside the RTX Spark Platform

Up to 1 PFLOPS
FP4 AI performance per RTX Spark Superchip.
Up to 6,144 CUDA cores
Blackwell RTX GPU architecture.
Up to 20-core Grace CPU
NVIDIA Grace CPU (Arm architecture).
Up to 128GB unified
Single memory pool shared by CPU + GPU.

FAQ

Frequently asked questions

What is confirmed about NVIDIA RTX Spark today: availability, Windows on Arm compatibility, and how it differs from NVIDIA DGX Spark.

When will this system be available, and how much will it cost?

NVIDIA states RTX Spark systems arrive beginning Fall 2026 in select regions, with ASUS and MSI systems first and Acer and GIGABYTE following. No official pricing has been announced by NVIDIA or any brand, in any market. Figures circulating in the technology press are analyst estimates rather than confirmed prices, so EMARQUE does not quote them.
For Malaysia, the ASUS ProArt P16 and P14 have been reported for Q3 2026 availability by Malaysian press; no other brand has given a Malaysia date. Contact EMARQUE and we will let you know as soon as local availability and pricing are confirmed: WhatsApp 012 627 2280 or business@emarque.co.
Will my existing Windows applications run on RTX Spark?

RTX Spark uses an Arm-based NVIDIA Grace CPU, so Windows runs x86 applications through Prism emulation, which Microsoft states is tuned for the microarchitecture of RTX Spark.
NVIDIA published its first GeForce driver for Windows on Arm in July 2026, alongside the CUDA Toolkit 13.4 developer preview, which adds native Windows Arm64 development for RTX Spark. Arm64EC lets a native Arm application keep using existing x64 libraries. NVIDIA is also partnering with Adobe to rearchitect Premiere and Photoshop for RTX Spark, work that is in progress rather than finished.
Applications compiled natively for Arm64 will run best, and most mainstream x86 software runs under emulation. If your work depends on plugin-heavy professional software, confirm its Arm64 support before ordering. EMARQUE can check compatibility for your workflow before you commit.
How is RTX Spark different from NVIDIA DGX Spark?

They are different products with similar names. RTX Spark is a Windows AI PC platform built on the RTX Spark Superchip, for laptops and compact desktops. DGX Spark is a Linux desktop AI supercomputer built on the GB10 Grace Blackwell Superchip, running NVIDIA DGX OS.
Different chip, different operating system, different purpose. If you need a local AI machine today rather than in Fall 2026, NVIDIA DGX Spark is available now from EMARQUE. For the full platform FAQ, see the NVIDIA RTX Spark lineup.

NVIDIA RTX Spark

Run AI models, create and game locally on a Windows PC built around NVIDIA's own silicon.

NVIDIA RTX Spark fuses a Blackwell RTX GPU with an Arm-based NVIDIA Grace CPU and up to 128GB of unified memory, reaching up to 1 petaflop of FP4 AI performance. It suits creators, AI developers and gamers who want local AI in a thin laptop or a small desktop. NVIDIA has confirmed an October 2026 launch.