top of page

NOVA, a Personal AI Agent Solution

NOVA (Neural On-device Virtual Assistant), powered by MLX-A1, is a fully self-contained personal AI agent solution that empowers users to build and run their own customized assistants locally, without reliance on cloud or servers.​

Supports pre-optimized LLMs, multimodal AI models, and user-defined workloads through Mobilint’s SDK - making it equally accessible to beginners experimenting with default setups and advanced users compiling their own models. ​

Demo-LLM cut-1.gif
MLX-A1_03-1.jpg

Sample demo use case of local LLM

MLX-A1.jpg

MLX-A1

MLX-A1 - AI box for desk and industrial deployment

AI Everywhere, at Scale

MLX-A1 is a compact standalone AI box 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_05.jpg

Technical specs

Processor

Intel® Core™ i5-13600HE Processor

NPU

MLA100 MXM (ARIES)

Performance

80 TOPS

Graphics

Intel® Iris® Xe Graphics

Memory

DDR5 32 GB (16 GB ✕ 2)

Storage

2280 NVMe 512 GB

LAN (Ethernet)

3 ✕ 2.5 Gbps

BIOS Function

AMI EFI 256 Mbit, SPI

Software

OS (Ubuntu 22.04), Mobilint SDK qb driver and runtime module

Power Supply

DC 19 V (Max 230 W)

Power (TDP)

70 W

Physical

Dimension:
178 ✕ 116 ✕ 67 mm
Weight: 1.3 kg

Max Resolution

HDMI: 4096 x 2304 @ 60Hz (HDMI 2.1)

Temperature

Operating: -20 °C to 60 °C with 0.5m/s air flow

I/O and connectivity​

MLX-A1_Front.png
MLX-A1_Back.png
MLX-A1_Front.png

Front ports

MLX-A1_Back.png

Back ports

Front ports: • Power botton
Back ports: • Reset button  • DC-In   • RJ45 (LAN) ✕ 3  • HDMI  • USB 3.2 ✕ 2  • USB 2.0 ✕ 4

Key features

Industrial-grade performance, laptop-class power consumption, and complete on-device AI capability. Ready for deployment today.

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​

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​

Rugged chassis built to withstand ambient temperature of –20 °C to 60 °C, weighing just 1.3 kg, for dependable performance anywhere.​

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.jpg

Discover how MLX-A1 can bring high-performance on-device AI to your operations.​

Accelerate Your AI Projects Today​

bottom of page