MLX-A1 Edge AI Box: For Desk and Industrial Deployment
MLX-A1 Edge AI Box: For Desk and Industrial Deployment
MLX-A1 Edge AI Box: For Desk and Industrial Deployment
Purpose-Built for AI Everywhere, at Scale
Purpose-Built for AI Everywhere, at Scale
Purpose-Built for AI Everywhere, at Scale
MLX-A1 Edge AI Box is a compact standalone AI mini PC engineered for high-performance, low-latency inference. Capable of running large language models, vision AI, and multimodal applications entirely offline, it ensures data privacy and operational reliability in any environment. With its 80 TOPS NPU, 70 W power envelope, and deployment-ready software stack, MLX-A1 bridges the gap between industrial-grade robustness and desktop accessibility.
MLX-A1 Edge AI Box is a compact standalone AI mini PC engineered for high-performance, low-latency inference. Capable of running large language models, vision AI, and multimodal applications entirely offline, it ensures data privacy and operational reliability in any environment. With its 80 TOPS NPU, 70 W power envelope, and deployment-ready software stack, MLX-A1 bridges the gap between industrial-grade robustness and desktop accessibility.
Built to Deliver
Built to Deliver
Built to Deliver
Industrial-grade performance, laptop-class power consumption, and complete on-device AI capability. Ready for deployment today.
Industrial-grade performance, laptop-class power consumption, and complete on-device AI capability. Ready for deployment today.
Independent AI Powerhouse
Independent AI Powerhouse
Independent AI Powerhouse
Run vision, transformer, and multi-modal models without cloud or servers. Fully self-contained with preloaded Linux OS (Windows optional) and Mobilint SDK.
80 TOPS NPU + AI-Centric Compute
80 TOPS NPU + AI-Centric Compute
80 TOPS NPU + AI-Centric Compute
Mobilint’s ARIES NPU AI acceleration paired with Intel® i5 CPU and Iris® Xe Graphics for versatile AI compute.
Industrial-Grade, Field and Desk Ready
Industrial-Grade, Field and Desk Ready
Industrial-Grade, Field and Desk Ready
Rugged chassis built to withstand ambient temperature of –20°C to 60°C, weighing just 1.3 kg, for dependable performance anywhere.
Specifications
Specifications
Specifications
CPU
Intel® Core™ i5-13600HE Processor
NPU
MLA100 MXM (ARIES)
AI performance
80 TOPS (Dense, INT8)
Graphics
Intel® Iris® Xe Graphics
Memory
DDR5 32 GB (16 GB x2)
Storage
2280 NVMe 512 GB
LAN (Ethernet)
3 x 2.5Gbps
BIOS Function
AMI EFI 256 Mbit, SPI
Software
OS (Ubuntu 22.04 or Windows (optional)), Mobilint SDK qb driver and runtime module
Power Supply
DC 19 V (Max 230 W)
TDP
70 W
Physical
Dimension: 178 x 116 x 67 mm
Weight: 1.3 kg
Max Resolution
HDMI: 4096 x 2304 @ 60Hz (HDMI 2.1)
Temperature
Operating: -20 °C to 60 °C with 0.5 m/s air flow
I/O and Connectivity
I/O and Connectivity
I/O and Connectivity
Front
Front
• Power botton
Rear
Rear
• Reset button, DC-In port
• RJ45 (LAN) ✕ 3
• HDMI port
• USB 3.2 port ✕ 2
• USB 2.0 port ✕ 4
Personalize Your Own AI Agent
Personalize Your Own AI Agent
Personalize Your Own AI Agent
Build a fully self-contained personal AI agent with MLX-A1 without relying on cloud or server infrastructure. Validated with LLMs such as EXAONE, Llama, and C4AI, as well as multimodal models like Qwen and Whisper, MLX-A1 executes user-defined workloads through Mobilint’s SDK qb, making it accessible both to beginners using default configurations and to advanced users compiling custom models.
Build a fully self-contained personal AI agent with MLX-A1 without relying on cloud or server infrastructure. Validated with LLMs such as EXAONE, Llama, and C4AI, as well as multimodal models like Qwen and Whisper, MLX-A1 executes user-defined workloads through Mobilint’s SDK qb, making it accessible both to beginners using default configurations and to advanced users compiling custom models.
Sample demo use case of local LLM
Sample demo use case of local LLM
From Lab Desks to Harsh Field Deployment
From Lab Desks to Harsh Field Deployment
From Lab Desks to Harsh Field Deployment
MLX-A1 enables real-time AI processing in environments where low latency, data security, and reliability are critical.
MLX-A1 enables real-time AI processing in environments where low latency, data security, and reliability are critical.
Desk AI Assistant
Desk AI Assistant
Smart City
Smart City
AI Research & Development
AI Research & Development
Smart Factory
Smart Factory
Security System
Security System
Robot Development
Robot Development
Have a use case in mind?
Let us know.
Get pricing, evaluation kits and engineering support to start building.
More ways to connect
Technology Partners
Build hardware, software or models that should run with Mobilint NPUs? Join our ecosystem and develop with us.
Become a Partner
Channel Partners
Bring Mobilint products to your market as an authorized reseller or distributor.
Join the Channel
Press & Media
Covering edge AI? Reach our team for interviews, press assets and company news.
Contact Press Team
Something else on your mind?
Contact the team
Have a use case in mind?
Let us know.
Get pricing, evaluation kits and engineering support to start building.
More ways to connect
Technology Partners
Build hardware, software or models that should run with Mobilint NPUs? Join our ecosystem and develop with us.
Become a Partner
Channel Partners
Bring Mobilint products to your market as an authorized reseller or distributor.
Join the Channel
Press & Media
Covering edge AI? Reach our team for interviews, press assets and company news.
Contact Press Team
Something else on your mind?
Contact the team
Have a use case in mind?
Let us know.
Get pricing, evaluation kits and engineering support to start building.
More ways to connect
Technology Partners
Build hardware, software or models that should run with Mobilint NPUs? Join our ecosystem and develop with us.
Become a Partner
Channel Partners
Bring Mobilint products to your market as an authorized reseller or distributor.
Join the Channel
Press & Media
Covering edge AI? Reach our team for interviews, press assets and company news.
Contact Press Team
Something else on your mind?
Contact the team
