top of page
ARIES, Ultra Performance AI Accelerator for On-Premises AI
Scalable AI Accelerator
ARIES
ARIES is an AI accelerator chip featuring a unique architecture that delivers high compute efficiency with low power consumption. With specifications of 80 TOPS performance at just 20 W, ARIES is ideal for heavy-duty edge applications such as robotics, smart factories, smart cities, and server infrastructures.
Designed for versatility in handling diverse AI tasks, ARIES has been successfully tested on over 400 deep learning models across CNN, RNN, and transformer architectures.
Product specs
NPU
ARIES (80 TOPS)
Memory Capacity
16 GB (Optional 32 GB) LPDDR4, 4X
Memory Bandwidth
66.7 GB/s
Host Interface
PCI Express Gen4 8-lane
TDP
25 W
AI Performance
MobileNet V2: 11,551 FPS
ResNet-50: 3,082 FPS
YOLO-11s: 784 FPS
YOLO-11l: 259 FPS
Key Features
Break Free From GPU Dependency Today
Cost Effective
Most cost-effective options for engineers prioritizing high price-performance ratio.
Flexibility
Deployment-ready architecture allows concurrent execution of up to 32 different deep learning models.
High Accuracy
World-leading lightweight technology maintains 99 % accuracy of existing models.
Easy to Use
User-friendly full-stack SDK that supports major ML frameworks including Tensorflow, Pytorch, ONNX.
Eco Friendly
Eco-friendly solution that maximizes data reuse and minimizes memory access for high energy efficiency.
Programmable
Supports more than 400 deep learning models, including SOTA models, with excellent performance.
Applications
Mobilint offers comprehensive solutions for a wide range of applications by integrating real-time artificial intelligence into edge environments such as smart cities, smart factories, edge data centers, and servers, and etc. Our technology delivers high performance, low power consumption, minimal heat generation, space efficiency, and cost competitiveness, enabling innovative and efficient solutions across industries.
bottom of page