In addition to P-Cores and E-Cores for generic computing tasks and the Intel Arc GPU for graphics-intensive tasks, the integrated Neural Processing Unit (NPU) called 'Intel AI Boost' contributes to the advanced neural processing capabilities of the entire computing architecture. According to Congatec, the integrated NPU enables efficient integration of advanced AI workloads with lower system complexity and lower costs compared to discrete accelerators. This makes the 'conga-TC700' COM Express Compact Computer-on-Modules based on Intel Core Ultra processors suitable for applications that require powerful real-time computing and high-performance AI functions, such as robots for use in operating theaters and medical imaging and diagnostic systems whose automatically generated critical findings can support medical professionals. Other application examples include situational awareness in industrial applications such as inspection systems, stationary robotic arms, autonomous mobile robots (AMRs) and automated guided vehicles (AGVs).

According to the provider, the Computer-on-Modules with Intel Core Ultra processors (codenamed Meteor Lake) are among the most energy-efficient x86 client SoCs on the market. Up to six P-cores and up to eight E-cores support up to 20 threads and enable the consolidation of distributed devices on one platform. The SoC-integrated Intel Arc GPU with up to eight Xe cores and up to 128 EUs can (pre-)process graphics with up to 2x 8K resolution and ultra-fast GPGPU-based image data. The integrated Intel AI Boost NPU makes the execution of machine learning algorithms and AI inferences particularly efficient. Up to 96 Gbyte DDR SO-DIMM with in-band ECC and 5600 MT/s performance enable high and energy-efficient data throughput with low latency.