AI Computing System Targets Edge Applications
Designed to bring server-grade AI performance to the edge, the MIC-743 from Advantech targets high-performance applications that include video language models (VLM) and large language models (LLMs). Leveraging the NVIDIA Jetson Thor T5000, the MIC-743 delivers up to 2,070 FP4 TFLOPs of AI performance, enabling real-time inferencing for complex edge applications.
Features include 2,560 CUDA cores and 96 Tensor cores for the processing power needed to handle AI workloads such as deep learning and computer vision.There's also 128 GB of LPDDR5X memory for sufficient bandwidth and capacity to handle large AI models, including VLM and LLM inferencing, without bottlenecks.
Able to run multimodal AI tasks simultaneously, the MIC-743 is well-suited for deployment in diverse environments such as factories, research labs, and development centers, integrating various sensors, cameras, and peripheral devices to quickly build complete AI solutions.
