NVIDIA is set to transform consumer computing with its latest RTX AI PC hardware, unveiled at the IFA Berlin consumer electronics and home appliances trade show.
At the heart of these new systems are the RTX GPUs, equipped with specialised AI hardware called Tensor Cores. These GPUs can deliver up to 686 trillion AI operations per second (TOPS) across the GeForce RTX 40 Series Laptop GPU lineup.
The new hardware also introduces a neural processing unit (NPU) for offloading lightweight AI tasks, complementing the GPU's capabilities. This combination allows for always-available AI capabilities, even without an internet connection, offering low latency and increased privacy for users.
NVIDIA's RTX GPUs have a significant advantage in the AI space, as noted by Jon Allman, an industry analyst at Puget Systems: "Many projects, especially within Windows, are built for and expect to run on NVIDIA cards. In addition to the wide software support base, NVIDIA GPUs also have an advantage in terms of raw performance."
The announcement includes new laptop models from manufacturers ASUS and MSI. These new laptops join a growing ecosystem of RTX AI PCs, with over 100 million GeForce RTX and NVIDIA RTX GPUs already in users' hands worldwide. The systems are designed to run large language models like Google's Gemma, Meta's Llama, and Microsoft's Phi significantly faster than CPUs, with NVIDIA claiming performance improvements of 10-100 times when using their TensorRT-LLM acceleration.