DX-H1 Quattro
by DEEPXSouth Korea
DEEPX edge AI accelerator for inference tasks in computer vision and physical AI. Details according to the manufacturer.
Price on requestWe obtain the quote for you.
Free and without obligation. OROBO brokers — you buy directly from the manufacturer or its dealer.
- Manufacturer
- DEEPX
- Country
- South Korea · Seongnam
- Category
- Edge AI modules
- Guide price
- on request
About the category
What it is
Edge AI modules are compact computers with a GPU or NPU, either built into your own device as a module or used as a ready-made box PC. They analyse images and sensor data on site — without cloud latency and without raw data leaving the plant. Industrial variants are designed for extended temperature ranges and continuous operation.
What companies use them for
- Visual inspection right at the production line.
- Control computer for robots, AMRs and autonomous machines.
- On-site video analytics for safety and traffic flows.
- Your own AI products in series, such as smart cameras or terminals.
What to look for when buying
- AI performance per watt and cooling inside the enclosure.
- The maker’s software stack: drivers, AI runtime, update commitments.
- Interfaces: cameras, fieldbus, network, power supply.
- Long-term availability and temperature range for the planned use.
Integration & effortEffort: medium
A box PC is quickly mounted; the effort lies in adapting and optimising models for the specific hardware and connecting it to cameras, controls and IT. With many devices in the field you also need a solution for remote maintenance and updates.
Software that fits
- NVIDIA JetPack (opens in a new tab)FreeSoftware stack for Jetson modules, including OS, drivers and AI libraries.
- NVIDIA DeepStream (opens in a new tab)FreeProcesses multiple camera streams efficiently on NVIDIA hardware.
- OpenVINO (opens in a new tab)Open source · Apache-2.0Optimises and accelerates models on Intel CPUs, GPUs and NPUs.
- ONNX Runtime (opens in a new tab)Open source · MITRuns models from different frameworks consistently on many chips.
- LiteRT (opens in a new tab)Open source · Apache-2.0Lightweight on-device runtime from Google, formerly TensorFlow Lite.
Licence details without guarantee — the project’s own licence is authoritative. We can set up and integrate it for you at a fixed price.
Simulation
How it runs in your operation
A simplified, typical sequence — not a recording of a real deployment.
The camera or sensor feeds images straight to the module.
The AI model detects objects in real time, without the cloud.
A signal goes to the controller, robot or signal light.
Collect results, retrain the model, roll out the update.
Brokering
How brokering works
- 01Request
Add the product to your request and tell us quantity, goal and timing. Free and without obligation.
- 02OROBO checks and obtains the quote
We check your need and intended use, screen buyer and seller against EU and US sanctions lists and obtain the quote from the manufacturer or its dealer. Your contact details only go to the seller with your consent.
- 03You buy directly from the manufacturer or its dealer
Contract, payment, delivery and warranty run directly between you and the seller. OROBO is neither seller nor importer and does not accept payments for goods.
Free for you: the seller alone sets the price. OROBO may receive a commission from the seller — on request we tell you whether and how much; it influences neither recommendations nor order. For now we broker for buyers in the EU, the EEA, Switzerland and the United Kingdom. Terms § 6b · Disclosure
Similar products
Product details and prices come from manufacturers’ public information (as of 3 Nov 2026, foreign currencies converted at the ECB rate). Prices are non-binding, rounded guide values excluding VAT, shipping and duties; only the seller’s quote is binding. Category texts are general information and do not replace a case-by-case assessment.