The model names of the new Aetina MXM GPU modules powered by NVIDIA RTX A1000, NVIDIA RTX A2000, and NVIDIA RTX A4500 are M3A1000-PP, M3A2000-VY, and M3A4500-WP, respectively. These models support CUDA Compute version 8.6, OpenGL 4.6, Vulkan 1.2, DirectX 12 Ultimate, and Shader Model 7.0, as well as Windows 10/11 64-bit and Linux 64-bit operating systems. For display and output, M3A1000-PP, M3A2000-VY, and M3A4500-WP all support up to 4x DisplayPort (DP) and 8K (7680 × 4320) resolution.
M3A1000-PP provides 6.66 TFLOPS peak FP32 performance and has 2048 CUDA cores, 16 RT cores, 64 Tensor cores, and 4 GB GDDR6 memory, while M3A2000-VY offers 8.25 TFLOPS peak FP32 performance and has 2560 CUDA cores, 20 RT cores and 80 Tensor cores, and 8 GB GDDR6 memory.
M3A4500-WP, with the highest computer power among all new models, provides 18.55 TFLOPS peak FP32 performance, and has 5888 CUDA cores, 80 RT cores, 184 Tensor cores, and 16 GB GDDR6 memory. The MXM GPU module, as well as M3A2000-VY, supports error correction code (ECC) memory for controlling errors in data over unreliable or unstable communication channels.
The new MXM GPU modules, with their compact designs, can be easily integrated into a variety of AI systems to boost the computing performance and run complex AI inference tasks. For these GPU modules, Aetina provides optional conformal coating service to make the modules capable of functioning normally in harsh environments, and ensures 5-year availability of the modules as well as exclusive technical supports to help its clients save maintenance costs and time for their long-term AI projects.
Moreover, the company offers MXM GPU modules powered by other NVIDIA GPUs including Quadro T1000, Quadro RTX3000, and Quadro RTX5000 to meet different levels of computer performance requirements from any AI-powered system developments.