NVIDIA RTX Spark Laptops

NVIDIA RTX Spark Laptops

Powerful laptops for developing AI models, controlling robots and running AI agents

An AI Laptop Supercomputer Wherever You Go

RTX Spark laptops usher in a new era in portable computing, delivering desktop-like performance and all-day battery life.

Built around a powerful NVIDIA Grace Blackwell SoC with up to 128GB of unified system memory, they provide up to 1 petaFLOP FP4 performance for AI workloads.

RTX Spark laptops are available in different models from multiple brands such as Asus, Microsoft and MSI.

NVIDIA Spark Diagram
FEATURES
NVIDIA GB10 Superchip
NVIDIA RTX Spark SoC

Cutting-edge SoC architecture delivers outstanding performance in AI, graphics and everyday workloads.

128GB Coherent System Memory
128GB of Coherent Unified System Memory

Run complex AI models locally without having to scale-out to the cloud for a lack of memory.

NVIDIA AI Software Stack
Thin & Light

RTX Spark laptops are around half the height, and 25% lighter, than traditional laptops with an x86 CPU and discrete GPU.

RT Cores

Unlike the DGX Spark, the RTX Spark has RT cores, providing photorealistic raytracing in creative applications and games.

All-Day Battery

The highly-integrated SoC architecture keeps power consumption low, giving you longer battery life.

Built for Windows 11

Unlike most AI systems, RTX Laptops run Windows 11, enabling you to run everyday applications and games with ease.

Maximise Your RTX Spark With Production Ready Software

NVIDIA AI Enterprise, available to purchase as an upgrade with RTX Spark, is a suite of frameworks and libraries, including NVIDIA NIM and NeMo microservices, that accelerate the development and deployment of AI projects. Leveraging pre-configured frameworks removes many of the manual tasks and complexity associated with software development, as each framework is tried, tested and optimised by NVIDIA. The less time spent developing, the greater the ROI on your AI hardware and data science investments.

Rather than trying to assemble thousands of co-dependent libraries and APIs from different authors when building your own AI applications, NVIDIA AI Enterprise removes this pain point by providing a full agentic AI software stack.

NVIDIA Inference Models Diagram

NVIDIA AI Workbench

You can speed up AI application development even further by using NVIDIA AI Workbench to build and test AI models in a safe and secure environment. Workbench is suitable whether you’re a working on a single development system such as a 3XS AI Workstation or DGX Spark, or scaling out onto more powerful hardware such as DGX servers or systems in the cloud. Watch the video opposite to see Workbench being used to deploy a content generation AI model.

FIND OUT MORE
NVIDIA RTX SPARK Workloads

NVIDIA RTX Spark Laptops

NVIDIA RTX Spark laptops from brands including Asus, Microsoft and MSI will be available soon from Scan.

GET IN TOUCH

Frequently Asked Questions (FAQ)

NVIDIA RTX Spark is a SoC comprising Grace CPU cores with a Blackwell GPU. It powers a range of thin and laptop laptops and small form factor desktop PCs from multiple brands such as Asus, Dell, Microsoft and MSI.

RTX Spark is ideal for developing AI models and running AI agents locally without having to connect to the cloud. As it has CUDA and RT cores, it can also be used for gaming and content creation applications, as well as everyday Windows applications.

Unlike most AI systems, RTX Laptops run Windows 11, enabling you to run everyday applications and games with ease.