NVIDIA has announced the RTX Spark Superchip, a new chip that combines AI processing and RTX graphics into a single platform for Windows PCs.
According to NVIDIA, the chip integrates a Blackwell-based RTX GPU with up to 6,144 cores and an ultra-efficient CPU with up to 20 cores.
It also supports up to 1 petaflop of FP4 AI performance and up to 128GB of unified memory.
NVIDIA states that the platform is built for AI “agents” to run tasks such as coding, content creation, and automation locally on the device.
It also highlights support for CUDA, which is NVIDIA’s software platform used for AI and computing workloads.
Additionally, the chip supports tools like real-time 3D rendering, AI-assisted editing, AV1 encoding, and streaming enhancements through NVIDIA Broadcast.
For gaming, it includes ray tracing, DLSS, Reflex, and G-SYNC support.
The RTX Spark platform is also expected to be used in thin laptops and compact desktops.
Devices mentioned include models from ASUS, Dell, HP, Lenovo, Microsoft, and MSI. NVIDIA has not yet detailed pricing or availability for RTX Spark-based products.
ManilaShaker is a tech media producing insightful and helpful content for our local and growing international audience. Our goal is to create a premier Philippine digital consumer electronics resource that provides the most objective reviews and comparisons globally.
