Skip to Content

Fanless Mini METISIV In-Vehicle Edge AI Computer

• Fanless Edge AI Computer • Model: FM-METISIV-50-12V 

Designed for uninterrupted in-vehicle inference, with intelligent vehicle-specific power management and a ruggedised, vibration-resistant chassis built for the road.

Tranquil AI and Axelera

Datasheet Get a Quote   

FEATURES

A rugged edge AI platform built for the vehicle.

The FM-METISIV-50-12V is an in-vehicle edge AI platform engineered for reliable, continuous operation in demanding mobile environments. Combining vehicle-specific power management, a ruggedized, vibration-resistant design, and on-device AI acceleration powered by the Axelera Metis AIPU, it enables low-latency inference directly inside the vehicle without depending on a continuous network connection.

Its standardized hardware platform simplifies deployment, maintenance, and lifecycle management across large fleets, making it ideal for fleet management, transportation, public safety, and field service applications where reliability, consistency, and edge performance are critical.

Axelera MetisAI acceleration - Axelera Metis® AIPU

Powered by the Axelera Metis® AI Processing Unit, a quad-core AI accelerator purpose-built for edge AI inference. It enables real-time object detection, classification, tracking, segmentation and multi-stream video analytics directly where data is generated, reducing bandwidth consumption, minimizing latency and keeping sensitive data on-site.

Rockchip RK3588  processor iconHost processor

An ARM-based Rockchip RK3588 host processor works alongside the Axelera Metis® AIPU to run the operating system, application software and the pre- and post-processing stages of the AI inference pipeline, providing a balanced platform for high-performance edge AI workloads.

AI Voyager software iconAI software - Voyager® SD

An ARM-based Rockchip RK3588 host processor works alongside the Axelera Metis® AIPU to run the operating system, application software and the pre- and post-processing stages of the AI inference pipeline, providing a balanced platform for high-performance edge AI workloads.

Intelligent ignition control iconIntelligent ignition control

The platform powers on and off with the vehicle ignition and manages power automatically to help protect the battery from drain. An anti-vibration design keeps operation stable through shock and movement.

Dual LAN Ports iconConnectivity

Dual LAN as standard, with optional Wi-Fi or 4G/LTE for connected and remotely managed deployments.

Anti vibration plate iconAnti-vibration plate

 A rugged anti-vibration design and fanless, no-moving-parts construction ensure reliable operation in high-shock, high-vibration environments.

Fanless, passively cooled design icoFanless, passively cooled design

A fully fanless, passively cooled architecture eliminates moving parts, reducing power consumption and maintenance requirements. Without fans to draw dust and debris into the enclosure, the platform is well suited to reliable long-term operation.

Rugged IP50 iconIP50-rated enclosure

IP50-rated enclosure protects internal components from dust ingress, helping ensure reliable operation in demanding industrial and in-vehicle environments.

IDEAL DEPLOYMENTS


Where the FM-METISIV-50-12V is ideal.

Keep AI inference running on the move, with processing that stays inside the vehicle wherever the journey takes it.

Fleet & transport iconFleet & transport

On-vehicle AI for vision, automatic number plate recognition (ANPR) and monitoring across the fleet.

Public-safety vehicles iconPublic-safety vehicles

Real-time detection and analytics on the move, without a continuous network connection.

Mobile robotics iconMobile robotics & AMRs

Navigation, obstacle detection and inspection on moving platforms.

Field service iconField service

Mobile inspection and monitoring at remote sites with intermittent connectivity.

THE CURRENT GENERATION

FM-METISIV-50-12V In-Vehicle Edge AI Computer

A summary of the platform's core capability. The full technical specification, I/O layout, and options are available on the datasheet.

Specifications


Processor

Rockchip RK3588 (ARM) - 8-core, up to 2.4 GHz

AI accelerator

Axelera Metis® AIPU

AI Performance

214 TOPS

AI software

Axelera Voyager® SDK (TensorFlow, PyTorch, ONNX) · Yocto Linux · Docker

Vehicle integration

Intelligent ignition control · anti-vibration design

Memory

16 GB LPDDR4X

Storage

64 GB eMMC (option: up to 8 TB SATA SSD)

Networking

2 × Gigabit LAN (optional Wi-Fi / 4G-LTE connectivity via internal M.2)

Power

12 V DC (3-pin Phoenix connector) · 9–20 W

Operating temperature

0 °C to 60 °C

Dimensions / Weight

80 × 336 × 221 mm · 9.4 kg

Rear view of In-vehcile rugged AI edge computer

For illustrative purpose 
Rear I/O: 
DC-In 12V, 2x RJ45 for LAN, 4x USB 3.2, 1x HDMI, 1x USB-C,Micro SD Slot

ENGINEERING & SUSTAINABILITY

Engineered in-house for performance and sustainability


The chassis is designed and precision-machined in-house, not sourced as an off-the-shelf enclosure. Its geometry is optimized for efficient passive cooling, structural strength and long-term reliability, with a design proven across extended operating temperatures.

The same engineering approach supports sustainability. The chassis is manufactured using repurposed and recycled aluminium wherever possible, while aluminium waste generated during production is recovered and recycled, reducing material waste without compromising performance.

Made in Britain

  • In-house designed and milled aluminium chassis

  • Optimized for efficient passive cooling

  • Proven reliability across extended operating temperatures

  • Repurposed and recycled aluminium

  • Production waste recycled

FREQUENTLY ASKED QUESTIONS.

The FM-METISIV-50-12V is built on the Axelera Metis® AIPU a quad-core AI Processing Unit using Axelera’s Digital In-Memory Computing (D-IMC) architecture, purpose-built for computer-vision inference at the edge.

The Metis AIPU is programmed with Axelera’s Voyager® SDK, which supports common frameworks PyTorch, ONNX and TensorFlow (via ONNX) alongside a library of pre-trained models. Model preparation follows Axelera’s pipeline-based workflow.

Yes. A single Metis AIPU can run multiple concurrent video streams and several parallel neural networks, which suits multi-camera analytics. Actual stream counts depend on the models and resolution used.

Yes. Inference runs locally, so data is processed where it is created reducing bandwidth use, keeping data on-site, and removing dependence on a continuous cloud connection.

Computer-vision tasks, object detection, classification, tracking, segmentation and video analytics.

The FM-METISIV-50-12V is passively cooled and fully fanless, with no moving parts, and adds an anti-vibration design for the mobile environment.

Intelligent ignition control powers the unit down in step with the vehicle ignition and manages power to help protect the battery from drain.

Yes. The FM-METISIV-50-12V has a ruggedised, anti-vibration, fanless design intended for continuous operation in mobile environments.

Controlled options operating-system deployment, software preload and branding are available and do not alter the certified platform baseline. Requirements that need mechanical, thermal, electronic or certification change route to Tranquil Studio.

Other platforms in the Edge AI Compute


FM-METIS-51

Fanless mini for industrial & outdoor edge AI



Explore


HCM-JON-32-41

Hybrid cooled Jetson Orin 32GB for robotics & vision

Explore


HCM-JON-64-41

In-vehicle rugged platform with ignition control



Explore

Tell us what you need your AI to do.

Share your use case, deployment environment and operational constraints, and we'll recommend the edge AI compute platform that's right for your application whether powered by Axelera Metis or NVIDIA Jetson. From standard platform selection to controlled configuration, every deployment is governed from day one.

Speak to an Engineer Back to Tranquil AI Overview