In 2019, artificial intelligence technology advanced rapidly, with AI applications becoming increasingly widespread. At that time, NVIDIA launched the “Jetson Nano,” an AI computer and development kit aimed at “embedded designers, researchers, and DIY makers,” priced at $499.
Recently, NVIDIA released an upgraded version of the Jetson Nano, currently the “most affordable” AI supercomputer in the series, along with its development kit, the 제트슨 오린 나노 슈퍼. It offers enhanced performance while cutting the price in half, now available for just $249.
According to NVIDIA’s official statement, the Nano Super targets “commercial AI developers, hobbyists, and students.” Indeed, this price is quite accessible for those new to generative AI, robotics, or computer vision technology. Perhaps this also indicates that the cost of using artificial intelligence for inference tasks is gradually decreasing.
Compared to the previous generation, the AI inference performance of Nano Super has increased by 1.7 times, with an overall performance boost of 70%, reaching 67 INT8 TOPS. Additionally, Nano Super’s memory bandwidth has increased to 102GB/s, a 50% improvement over the previous generation; the CPU frequency has also been raised from 1.5GHz to 1.7GHz.
The entire Nano Super development kit includes the Jetson Orin Nano 8GB System-on-Module (SoM) and a reference carrier board. The SoM is equipped with an NVIDIA Ampere architecture GPU and a 6-core Arm CPU, supporting multiple simultaneous AI application pipelines and high-performance inference.
Moreover, it supports connecting up to four cameras, offering higher resolution and frame rates than previous versions.
NVIDIA claims that the performance improvements of Nano Super benefit all popular generative AI models and transformer-based computer vision. Not only that, since the hardware of the Nano Super suite is essentially the same as its predecessor, the Orin Nano, users who previously purchased the Orin Nano can also experience the performance boost of the Nano Super by installing a software update (JetPack SDK).
NVIDIA calls this a “gift that keeps on giving.”
With the support of the NVIDIA ecosystem, developers can access tutorials from the NVIDIA Jetson AI Lab, receive support and assistance from the broader Jetson community, or draw inspiration from projects created by other developers.
NVIDIA states that whether creating LLM chatbots based on retrieval-augmented generation, building visual AI agents, or deploying AI-based robots, the Nano Super is the “ideal solution” and they look forward to it accelerating AI-driven robotics across multiple industries.
As the field of artificial intelligence gradually shifts from task-specific models to more general foundational models, the Nano Super undoubtedly provides tech enthusiasts with the “most affordable” accessible platform to turn ideas into reality. As NVIDIA said:
Now everyone can unlock new possibilities with generative AI.
출처 이판르
면책 조항: 위에 제시된 정보는 Chovm.com과 독립적으로 ifanr.com에서 제공합니다. Chovm.com은 판매자와 제품의 품질과 신뢰성에 대해 어떠한 진술과 보증도 하지 않습니다. Chovm.com은 콘텐츠의 저작권과 관련된 위반에 대한 모든 책임을 명시적으로 부인합니다.
