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
Hailo AI Accelerators.
Maximum AI per watt. Minimum cost per camera.
Purpose-built AI accelerators delivering 26 TOPS at just 2.5W — the highest TOPS-per-watt ratio in the industry. M.2 and PCIe modules that add AI acceleration to any existing system, instantly upgrading NVRs, edge PCs, and cameras.
Three Hailo accelerators. Drop-in AI upgrade.
Add AI inference to any existing edge device via M.2 or PCIe. No new system needed — Hailo modules upgrade your current hardware to AI-capable in minutes.
Hailo-8
- Architecture Dataflow (non-von Neumann)
- Power 2.5W typical
- Efficiency 10.4 TOPS/W
- Form Factor M.2 2242 / M.2 2280
- Interface PCIe Gen3 x4
- Temp 0°C to 80°C
Hailo-15H
- Architecture Dataflow + ISP
- Power 3.5W typical
- ISP 4K60 HDR ISP built-in
- Form Factor BGA / Module
- Video H.264/H.265 encoder
- Temp 0°C to 85°C
Hailo-10H
- Architecture Dataflow Gen2
- Power 3W typical
- Efficiency 13+ TOPS/W
- Form Factor M.2 / PCIe
- Interface PCIe Gen4 x4
- Temp Industrial range
Why Hailo for edge AI acceleration
10.4 TOPS/W Efficiency
Dataflow architecture achieves 10.4 TOPS per watt — 4× more efficient than GPU-based solutions. AI inference at milliwatt-level power budgets.
M.2 / PCIe Drop-In
Standard M.2 2242/2280 and PCIe x4 interfaces. Plug into any existing NVR, edge PC, or gateway — no redesign, no new enclosure, instant AI upgrade.
Multi-Chip Scaling
Stack up to 8 Hailo-8 chips on a single PCIe card for linear scaling to 208 TOPS. Scale AI performance by adding modules — no system replacement needed.
Lowest Cost per Stream
Process 8–16 camera streams at $10–12 per camera. The most cost-effective AI inference for multi-camera surveillance, retail, and smart city deployments.
Fanless Operation
2.5W power means zero active cooling. Fanless, silent, vibration-free AI acceleration from 0°C to 80°C — perfect for indoor, outdoor, and industrial environments.
Dataflow Architecture
Non-von Neumann architecture eliminates memory bandwidth bottleneck. AI model streams through hardware — deterministic latency, zero memory wall limitations.
Where Hailo accelerators deliver
AI-NVR / DVR Upgrade
Add M.2 Hailo-8 to existing NVR hardware. Instant AI analytics — people counting, intrusion detection, ANPR — without replacing your recording infrastructure.
Smart City Retrofit
Upgrade existing traffic cameras and city infrastructure with Hailo-powered edge AI. PCIe cards add AI to junction boxes already deployed across cities.
Retail Multi-Camera
8–16 cameras per Hailo-8 module. Heatmaps, queue analytics, shelf compliance, and loss prevention from a single low-power accelerator card.
Access Control & Gates
Process 12+ lanes simultaneously at under 10W total. Face recognition, vehicle identification, and crowd flow at stadium gates, metro stations, and building entries.
RDP integration for Hailo accelerators
Multi-Chip PCIe Cards
RDP-designed PCIe carrier cards with 2×, 4×, or 8× Hailo-8 modules for 52–208 TOPS in a single PCIe slot. Validated thermal and power delivery.
AI-NVR System Integration
Complete AI-NVR systems: RDP rack servers + Hailo accelerator cards + NVR software. Pre-configured, tested, and ready for deployment from 8 to 128 cameras.
Make-in-India Certified
GeM-listed AI-NVR and edge AI systems. BIS certified. Eligible for smart city, surveillance, and government security projects under MII guidelines.
Software Ecosystem Support
Pre-validated with TAPPAS SDK, GStreamer pipelines, and major VMS platforms. RDP provides deployment engineering for ISV integration and model optimisation.
Ready to bring AI to the edge?
Tell us your use case, performance requirements, and deployment scale. We’ll recommend the right platform, configure the right Edge PC, and deliver validated hardware — from pilot to production.