In a serious leap for edge AI processing, NTT Corporation has announced a groundbreaking AI inference chip that may process real-time 4K video at 30 frames per second—using lower than 20 watts of power. This latest large-scale integration (LSI) chip is the primary on this planet to attain such high-performance AI video inferencing in power-constrained environments, making it a breakthrough for edge computing applications.
Revealed during NTT’s Upgrade 2025 summit in San Francisco, the chip is designed specifically for deployment in edge devices—hardware positioned physically near the source of information, like drones, smart cameras, and sensors. Unlike traditional AI systems that depend on cloud computing for inferencing, this chip brings powerful AI capabilities on to the sting, drastically reducing latency and eliminating the necessity to transmit ultra-high-definition video to centralized cloud servers for evaluation.
Edge Computing vs. Cloud Computing: Why It Matters
In traditional cloud computing, data from devices like drones or cameras is shipped to distant data centers—often positioned tons of or hundreds of miles away—where it’s processed and analyzed. While this approach offers virtually unlimited compute power, it introduces delays as a result of data transmission, which is problematic for real-time applications like autonomous navigation, security monitoring, and live decision-making.
Against this, edge computing processes data locally, on or near the device itself. This reduces latency, preserves bandwidth, and enables real-time insights even in environments with limited or intermittent web connectivity. It also enhances privacy and data security by minimizing the necessity to transmit sensitive data over public networks.
NTT’s latest AI chip fully embraces this edge-first philosophy—delivering real-time 4K video evaluation directly inside the device, without counting on the cloud.
A Latest Era for Real-Time AI on Drones and Devices
With this chip installed, a drone can detect people or objects from as much as 150 meters (492 feet)—the legal altitude limit for drones in Japan. That’s a dramatic improvement over traditional real-time AI systems, that are generally limited to a 30-meter range as a result of lower resolution or processing speed.
This advancement enables a bunch of recent use cases, including:
-
Infrastructure inspections in hard-to-reach places
-
Disaster response in areas with limited connectivity
-
Agricultural monitoring across wide fields
-
Security and surveillance without constant cloud uplinks
All of that is achieved with a chip that consumes lower than 20 watts—dramatically lower than the tons of of watts required by GPU-powered AI servers, that are impractical for mobile or battery-powered systems.
Contained in the Chip: NTT’s Proprietary AI Inference Engine
The LSI’s performance hinges on NTT’s custom-built AI inference engine, which ensures high-speed, accurate results while minimizing power use. Key innovations include:
-
Interframe correlation: By comparing sequential video frames, the chip reduces redundant calculations, improving efficiency.
-
Dynamic bit-precision control: This method adjusts the numerical precision required on the fly, using fewer bits for easier tasks, conserving energy without compromising accuracy.
-
Native YOLOv3 execution: The chip supports direct execution of You Only Look Once v3, considered one of the fastest real-time object detection algorithms in machine learning.
These combined features allow the chip to deliver robust AI performance in environments previously considered too power- or bandwidth-limited for advanced inferencing.
Path to Commercialization and the IOWN Vision
NTT plans to commercialize the chip inside fiscal yr 2025 through its operating company, NTT Progressive Devices Corporation.
Researchers are already exploring its integration into the Progressive Optical and Wireless Network (IOWN)—NTT’s next-generation infrastructure vision geared toward overhauling the digital backbone of contemporary society. Inside IOWN’s Data-Centric Infrastructure (DCI), the chip would benefit from the All-Photonics Network for ultra-low latency, high-speed communication, complementing the local processing power it brings to edge devices.
NTT can also be collaborating with NTT DATA, Inc. to mix the chip’s capabilities with its Attribute-Based Encryption (ABE) technology, which enables secure, fine-grained access control over sensitive data. Together, these technologies will support AI applications that require each speed and security—corresponding to in healthcare, smart cities, and autonomous systems.
A Legacy of Innovation and a Vision for the Future
This AI inference chip is the newest demonstration of NTT’s mission to empower a sustainable, intelligent society through deep technological innovation. As a world leader with over $92 billion in revenue, 330,000 employees, and $3.6 billion in annual R&D, NTT serves greater than 75% of Fortune Global 100 corporations and tens of millions of consumers across 190 countries.
Whether it’s drones flying beyond the visual line of sight, cameras detecting events in real-time without cloud dependency, or securing data flows with attribute-based encryption, NTT’s latest chip sets the stage for the subsequent frontier in AI at the sting—where intelligence meets immediacy.
