Spectra PowerBox 500: Edge AI server with MXM GPU modules


Machine vision ranges from simple environmental perception applications such as positioning, measuring, identifying and sorting objects, to more complex vision-controlled automation functions. For this range of applications, a flexibly configurable embedded system helps the system integrator.
The powerful Spectra PowerBox 500 Series Edge AI servers are extremely scalable – the integrated Intel® C246 chipset supports more than 20 different 8th and 9th Gen Intel® processors from Celeron® to Xeon®. The integrated graphics controller offers outstanding graphics performance. The required storage capacity is realised by two 2.5″ SATA drives and is expandable with the help of several mSATA and NVME SSD slots.
The real flexibility is offered by the new Quadro® MXM GPU modules MXM-RTX3000 and MXM-T1000. They use the NVIDIA® Quadro® Turing™ GPU architecture based on the latest 12nm process. The MXM-RTX3000 features 1920 CUDA cores, 5.3 TFLOPS peak FP32 high-end computing performance, parallel integer execution, AI computing tensor core and specialised RT core for ray tracing. The MXM-T1000 features 896 CUDA cores, 2.6 TFLOPS peak FP32 computing performance and only 50 W power consumption for ultra-low power high-speed computing.
Both models support GDDR6 memory. The MXM-RTX3000 has a single card capacity of up to 6 GB and a memory bandwidth of 336 GB/s. The MXM-T1000 has a capacity of 4 GB and a memory bandwidth of 192 GB/s. The fast memory smoothes data reading and multiplies computing power.
A highly effective cooling concept enables fanless operation. With the processor and GPU module installed at maximum capacity, it is very easy to connect an external cooling system.