ASUS Unveils Ascent GX10 AI Supercomputer with NVIDIA Superchip

Mar 20, 2025
ASUS has introduced the Ascent GX10 AI supercomputer, powered by the NVIDIA GB10 Grace Blackwell Superchip, offering up to 1,000 AI TOPS processing and 128GB unified memory.
ASUS Unveils Ascent GX10 AI Supercomputer with NVIDIA Superchip

ASUS has announced its new AI supercomputer, the Ascent GX10, powered by the NVIDIA GB10 Grace Blackwell Superchip, announced in a press release. This compact device delivers up to 1,000 trillion operations per second (TOPS) of AI performance, making it a powerful tool for developers, AI researchers, and data scientists.

The Ascent GX10 features a cutting-edge architecture with a Blackwell GPU, a 20-core Arm CPU, and NVLink-C2C technology, which enhances AI workloads by providing a cohesive CPU+GPU memory model. This setup allows the system to handle AI models with up to 200-billion parameters, supported by 128GB of unified system memory.

Designed for scalability, the GX10 can be configured as a standalone or private-cloud system, and two units can be connected via ConnectX-7 NICs to manage even larger models. The device is set to be available for pre-order in Q2 2025, with more information accessible through the ASUS website.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.