"The DGX Spark is powered by Nvidia's new GB10 chip, a compact version of the Grace-Blackwell Superchip that is also used in the large NVL72 data center systems. The GB10 combines a GPU and CPU in a single system-on-a-chip and uses an NVLink connection with a bandwidth of 600 GB/s. The GPU can deliver up to 1 petaFLOP of FP4 performance or 31 teraFLOPS at FP32 precision, comparable to a high-end consumer card, but with significantly more memory."
"The CPU was developed in collaboration with MediaTek and consists of 20 ARMv9.2 cores: 10 high-performance X925 cores and 10 energy-efficient Cortex A725 cores. The CPU and GPU share the same pool of LPDDR5x memory, providing a bandwidth of 273 GB/s. This integrated architecture allows the system to handle memory-intensive workloads much more efficiently than traditional workstations."
"The DGX Spark was announced earlier this year at CES under the name Project Digits. The system is about the same size as an Intel NUC and runs a modified version of Ubuntu Linux rather than Windows. According to Nvidia, the device is intended for developers in artificial intelligence, robotics, and data science who want to run models with up to 200 billion parameters without relying on large server setups."
The DGX Spark is a compact Grace Blackwell workstation offering up to one petaFLOP of computing power and 128 GB of shared memory. The system is similar in size to an Intel NUC and runs a modified Ubuntu Linux. The GB10 system-on-a-chip integrates GPU and CPU with a 600 GB/s NVLink and delivers up to 1 petaFLOP FP4 or 31 TFLOPS FP32. The 20-core ARMv9.2 CPU (10 X925 and 10 Cortex A725 cores) and GPU share LPDDR5x memory at 273 GB/s. The starting price is about $3,000, targeting developers and researchers for local AI model development.
Read at Techzine Global
Unable to calculate read time
Collection
[
|
...
]