Cost-Efficient. Low Power.
Unlock high-performance AI inference for vision, language, and edge intelligence with M.2 Module.
Geniatech AIM-M2 is an M.2 AI accelerator module powered by the 40 TOPS Kinara Ara-2 NPU. It delivers high-performance, low-power AI inference for edge AI applications, including generative AI tasks like Stable Diffusion and LLaMA-2.
The M.2 form factor allows you to add local ML acceleration to products such as embedded platforms, mini-PCs, and industrial gateways that have a compatible M.2 card slot.
-
40 TOPS AI performance powered by Kinara Ara-2
-
Plug-and-play M.2 form for easy system integration
-
Run large AI models with ultra-low latency and power consumption
-
Efficiently process multiple models without performance loss.
- Hassle-free evaluation and software integration with drivers and SDK

Specification
ML accelerator | Kinara Ara-2 AI processor: 40 TOPS (int8); 12W |
Connector | M.2 (M-Key, 4-lane PCIe Gen 4) |
Dimensions (W x L) | 22mm x 80mm |
Memory | 8GB LPDDR4 (16GB optional) |
Operating System Support | Linux, Windows |
Temperature | 0℃~70℃ |
AI Frameworks | TensorFlow, PyTorch, ONNX |
Performance | Stable Diffusion 1.4: 7 sec/image Llama2-7B: 12 output tokens/sec MobileNetV1 SSD: 974 IPS (1.03 ms latency) |
Security | Secure Boot, Root-of-trust processor, encrypted interface |
Reviews
There are no reviews yet.