top of page


산업용 보드/모듈 NVIDIA RTX 3500 GPU

The MX3500A-SP MXM 3.1 Type B module features an NVIDIA RTX 3500 Ada Generation Embedded GPU based on the NVIDIA Ada Lovelace architecture.



  • NVIDIA RTX 3500 Ada Generation Embedded GPU based on NVIDIA Ada 

  • Lovelace architecture

  • 5120 CUDA cores, 40 RT cores and 160 Tensor cores

  • 23.04 TFLOPS peak FP32 performance

  • 12GB GDDR6 memory

  • PCIe Gen 4 x16 interface

  • Support Error Correction Code(ECC)


The MX3500A-SP MXM 3.1 Type B module features an NVIDIA RTX 3500 Ada Generation Embedded GPU based on the NVIDIA Ada Lovelace architecture. This architecture delivers revolutionary ray tracing and AI performance for graphics and neural networks. With dramatically higher baseline performance tailored for ray tracing and neural graphics workloads, it marks a major advancement in capabilities. The module enables outstanding gaming, content creation, professional graphics, AI acceleration, and compute power.

● Advanced GPU engine compared to Ampere Architecture

Powered by the NVIDIA RTX 3500 Ada Generation Embedded GPU featuring the NVIDIA Ada Lovelace architecture, the MX3500A-SP module delivers higher performance from its Ray Tracing and Tensor cores compared to GPUs built on the previous architecture. This enables more advanced ray traced graphics and AI capabilities.

● Supports Error Correction Code(ECC)

ECC provides higher reliability for compute applications that are sensitive to data corruption, especially important in large-scale cluster computing environments where GPUs process extremely large datasets and/or run applications for extended periods.

● PCIe Gen 4 x16 interface

PCIe Gen 4 interface in Ada Lovelace Architecture GPUs delivers faster sequential data transfer than PCIe Gen 3 interface. The increased throughput unlocks higher performance, lower latency and better scalability in Ada Lovelace architecture over previous generations.

● Conformal coating optional service for rugged applications

For all series of MXM modules, Aetina offers conformal coating optional service, suitable for harsh environments such as massive-computing embedded applications.

● 5-year long-term supply

During long development period, Aetina ensures MXM modules with 5-year availability and exclusive technical support, helping customers to save maintenance cost and time.

bottom of page