Nvidia, the Santa-Clara-based American tech company, debuts a new compact generative AI supercomputer that fulfills performance needs at a lower price with a software upgrade. It has recently unveiled the NVIDIA Jetson Orin Nano Super Developer Kit. It gives a performance boost to PCs that suits people from enthusiasts to AI developers, students to hobbyists. It suits them all with unparalleled performance and efficiency. 

The tool can support tasks ranging from creating LLM chatbots based on retrieval-augmented generation to building a visual AI agent or deploying AI-based robots, it has got it all! 

Its performance ‘

It can deliver as much as a 1.7x leap in generative AI inference performance, a 70% increase in performance to 67 INT8 TOPS, and a 50% increase in memory bandwidth to 102GB/s compared with its predecessor. The tool gives the best performance with all popular generative AI models and transformer-based computer vision. Supporting up to four cameras, it provides enhanced resolution and higher frame rates as compared to its previous versions.

Check its size! 

Components of the tool 

The developer kit, featuring a Jetson Orin Nano 8GB system-on-module (SoM) and a reference carrier board, offers an ideal platform for prototyping edge AI applications. Equipped with an NVIDIA Ampere architecture GPU with tensor cores and a 6-core Arm CPU, the SoM enables multiple concurrent AI application pipelines and delivers high-performance inference. 

Also read: Nvidia and SoftBank Launch Strategic Partnership to Drive AI Revenue in Telecommunications

Upgrade the Nano 

The new software updates for the Jetson Orin Nano Super will enhance generative AI performance for existing Jetson Orin Nano Developer Kit users, making it an ideal choice for those looking to develop skills in generative AI, robotics, or computer vision.

Availability 

The software updates, designed to boost generative AI performance by 1.7X, will also be available for the Jetson Orin NX and Orin Nano series of system-on-modules.

To your surprise, Nvidia is also planning an Indigenous chip in India, read about it at: Nvidia and Indian Government in Talks Exploring A Co-developed Chip