ASUS reveals unusual mini-PC for running neural networks |
|
 |
|
|
ASUS has announced an unusual Ascent GX10 mini-PC equipped with NVIDIA GB10 Grace Blackwell ?superchip?. The compact device is designed to work with neural networks and is capable of running language models on 200 billion parameters. The proprietary ?green? chip is equipped with ten high-performance Cortex-X925 cores and the same number of auxiliary Cortex-A725 cores. The declared computing power of the novelty in AI-operations is 1000 TOPS: it is approximately three times less than that of NVIDIA GeForce RTX 5090. At the same time, due to 128 GB of RAM  Random Access Memory (RAM) is the place in a computer where the operating system, application programs, and data in current use are kept so that they can be quickly reached by the computers processor., the mini-PC can run more ?heavy? AI models and can also work as part of a computing cluster.NVIDIA GB10 is connected to the device's CPU CPU is the abbreviation for central processing unit (the processor). The CPU is the brains of the computer where most calculations take place. via NVLink interface. This allows them both to access RAMRandom Access Memory (RAM) is the place in a computer where the operating system, application programs, and data in current use are kept so that they can be quickly reached by the computers processor.. The computer supports SSD-storage up to 4 TB. Other characteristics of the device, as well as its announcement date and retail price have not been announced yet. |
