India's value-for-money IT hardware brand
14 years. 28,000 sq ft. 100,000+ devices. From desktops to data center — designed, engineered, and manufactured in India.
Why choose RDPDesktops to data center, all Make in India
14 product categories across compute, AI, and data center. Deployment-ready from our 28,000 sq ft facility.
Download Product CatalogSovereign AI infrastructure
End-to-end AI compute under one sovereign umbrella. Designed here. Manufactured here. Supported here.
Talk to a Solutions Architect
SLA-driven. Not ticket-driven.
Warranty. SLA. On-site service. Account management. Every commitment documented, every response time defined.
Download SLA Commitment
Built on process, not promises
ISO 9001. PLI 2.0. SOP-led manufacturing. The systems behind every device we ship.
Our Story
RDP-IOT-OPRJ-IX1-01
Compact AI Edge Inference Box with NVIDIA Jetson Orin NX · Up to 100 TOPS · CUDA-Accelerated
Key Applications
- Edge AI Inference (Real-time)
- Computer Vision & Object Detection
- Retail Analytics & Footfall
- License Plate / ANPR
- Smart City Video Analytics
- Factory Floor AI Inspection
- Healthcare Imaging Edge AI
- Conversational AI at the Edge
Key Features
- NVIDIA Jetson Orin NX System-on-Module — Ampere GPU + 8-core Arm Cortex-A78AE CPU
- Up to 100 TOPS AI inference performance — INT8 sparse
- 16GB LPDDR5 unified memory (CPU + GPU shared)
- 256GB NVMe SSD for OS, applications, and AI models
- Pre-installed NVIDIA JetPack SDK · CUDA · cuDNN · TensorRT · DeepStream
- Compact desktop / DIN-rail mount · 3/3/1 warranty · Make in India
Product SKU
| Model | RDP-IOT-OPRJ-IX1-01 |
|---|---|
| Platform Reference | Based on NVIDIA Jetson Orin NX reference design |
| Origin | Designed and integrated in India by RDP Technologies Limited, Hyderabad |
AI Compute & SoC
| SoC |
|
|---|---|
| AI Performance | Up to 100 TOPS (INT8 sparse) |
| GPU Memory | Unified — shared with system memory (16GB LPDDR5) |
| AI Frameworks | NVIDIA JetPack · CUDA · cuDNN · TensorRT · DeepStream · NVIDIA Triton Inference Server |
| Inference Stack | Pre-installed and validated for object detection, image classification, NLP, ASR |
System Memory
| Memory | 16GB LPDDR5 (unified CPU + GPU memory) |
|---|---|
| Memory Bandwidth | 102.4 GB/s |
| ECC | SECDED ECC supported |
Storage
| Primary Storage | 256GB NVMe SSD (M.2 2280, PCIe Gen4) |
|---|---|
| Storage Expansion | 1× M.2 2280 PCIe Gen4 (configurable up to 2TB) |
| eMMC | 64GB onboard eMMC (boot) |
| Secondary Slot | 1× microSD card slot (UHS-I, for media / data offload) |
Connectivity & I/O
| LAN | 2× Gigabit Ethernet (RJ45) · 1× 10GbE option |
|---|---|
| Wireless | Wi-Fi 6 · Bluetooth 5.2 (optional) |
| Cellular | 4G LTE / 5G via M.2 slot (optional) |
| USB | 4× USB 3.2 Gen 2 · 1× USB-C (with DisplayPort Alt Mode) |
| Display | 1× HDMI 2.1 · 1× DisplayPort 1.4a · USB-C DP Alt |
| Camera | 4× MIPI CSI-2 camera lanes (for direct camera connection) |
| Serial | 2× RS-232/422/485 (isolated) · 1× CAN bus |
| GPIO | 16× DI / 16× DO (digital I/O) — opto-isolated |
System BIOS & Management
| Boot | UEFI boot · Secure Boot · NVIDIA Cboot bootloader chain |
|---|---|
| Remote Management | NVIDIA Fleet Command-ready · Over-the-air (OTA) updates |
| Monitoring | System health · thermal monitoring · per-component power telemetry |
| Watchdog | Hardware watchdog timer · auto-recovery |
Security
| Hardware | NVIDIA Jetson Secure Boot · Cryptographic accelerator · Optional TPM 2.0 module |
|---|---|
| Security Features |
|
Chassis & Physical
| Form Factor | Compact desktop / DIN-rail mount (industrial) |
|---|---|
| Dimensions (W × D × H) | 180 × 130 × 60 mm (7.1" × 5.1" × 2.4") |
| Weight | Approximately 1.5 kg (3.3 lbs) |
| Mounting | Desktop · DIN-rail · VESA-mount (75/100mm) · Wall-mount |
| Chassis Material | Aluminum (passive heat dissipation) |
System Cooling
| Cooling Method | Fanless passive cooling (standard) · Optional active fan for high-temp environments |
|---|---|
| Operating Temperature | -10°C to 55°C (14°F to 131°F) |
| Non-operating Temperature | -30°C to 70°C (-22°F to 158°F) |
| Operating Humidity | 5% to 95% (non-condensing) |
| Vibration / Shock | IEC 60068-2-64 vibration / IEC 60068-2-27 shock compliant |
Power Supply
| Input Voltage | DC 9–36V (wide-range industrial input) · Optional 12V/24V adapter |
|---|---|
| Power Consumption | 15W typical · 25W max under full AI inference load |
| Power Connector | 3-pin terminal block (with reverse polarity protection) |
| PoE+ Option | Optional IEEE 802.3at PoE+ powered device support |
OS Support, Compliance & Warranty
| Operating System |
|
|---|---|
| AI Software Stack | NVIDIA JetPack · CUDA · cuDNN · TensorRT · DeepStream · Triton Inference · NVIDIA Metropolis |
| Compliance & Certifications | BIS · CE · FCC · RoHS · ISO 9001 · MeitY Recognised · GeM Listed |
| Warranty | 3 years parts · 3 years labor · 1 year cross-ship (3/3/1 standard) |
| Support | PAN-India SLA-backed service · OEM-friendly 5+ year availability commitment |
Download technical resources, manuals, and edge AI deployment guides for RDP-IOT-OPRJ-IX1-01.
Request a quote for RDP-IOT-OPRJ-IX1-01
Tell us your edge AI use case — retail analytics, computer vision, smart city deployment, or factory floor inspection. Our edge AI architects will spec the right configuration and provide a quote.
Standard lead time: 5 business days. Multi-unit fleet deployments planned in coordination with your rollout team.