MLA400
Quad-ARIES PCIe card delivering 320 TOPS of AI inference
Overview
MLA400
Featuring a quad-ARIES architecture, the MLA400 PCIe card delivers massive AI throughput with outstanding power efficiency. Four ARIES NPUs on a single full-height half-length card provide 320 TOPS of combined inference performance.
Designed for powerful and efficient AI acceleration from local workstations to smart city infrastructures. Models compiled for MLA100 work on MLA400 without recompilation — the multi-NPU runtime handles automatic workload distribution across all four ARIES NPUs.
Authorised Mobilint Distributor
Official sales, integration & support services
Features
Key Capabilities
Same SDK, Same Models
Models compiled for MLA100 work on MLA400 without recompilation. Seamless scale-up.
Multi-NPU Runtime
Automatic workload distribution across all four ARIES NPUs with dynamic balancing.
Framework Support
Import from PyTorch, TensorFlow, ONNX, TFLite, and Keras — same workflow as single-ARIES products.
Specifications
Technical Details
Applications
Use Cases
On-Premises AI Servers
High-density, low-power inference for edge server units. Multiple MLA400 cards scale linearly in a single chassis.
PCs & Workstations
Plug-and-play PCIe acceleration for local AI development, testing, and deployment workflows.
Video Analytics
Real-time multi-channel video processing with minimal thermal overhead. Ideal for surveillance at scale.
AI Infrastructure
Scalable compute for enterprise- or city-wide deployment of vision AI and autonomous systems.
Downloads
Documents & Datasheets
Request product documentation and our team will email you the files directly.
MLA400 Datasheet
datasheet
Related
Other Mobilint Products
Ready to Get Started with the MLA400?
Contact our team for pricing, technical questions, or to request an evaluation unit.