Geniatech AIM-M-K is a new upcoming M.2 AI-accelerator cards with up to 16GB of LPDDR4 memory that integrate NXP Ara240 NPU for local AI inference

[Hedda]

FYI, Geniatech has shared some information about the AIM-M-K (and AIM-B2) AI accelerator modules based on the NXP Ara240 NPU with "designs target edge inference workloads, offering up to 40 TOPS of INT8 performance for applications such as computer vision, transformer models, and generative AI."

• https://linuxgizmos.com/geniatech-aim-m-k-and-aim-b2-integrate-ara240-for-local-ai-inference/

  • https://www.geniatech.com/product/aim-m2/

    • https://shop.geniatech.com/product/m2-ai-inference-acceleration-module/

"The AIM-M-K adopts a standard M.2 2280 (M-key) form-factor and connects over a PCIe Gen4 x4 interface, allowing it to be integrated into existing x86 and Arm-based systems without requiring changes to the base hardware. That module will be available with up to 16 GB of LPDDR4 memory for handling larger models and high-throughput workloads."

"The AIM-M-K M.2 module is listed at $645, although it is not currently available for retail purchase. Geniatech indicates that samples can be requested for prototype development. Pricing and availability for the AIM-B2 module have not been disclosed."