Nvidia has officially unveiled its next-generation RTX 50-series GPUs, including the high-end RTX 5090 and RTX 5080, which promise major performance improvements over their predecessors.
The RTX 5090, priced at $1,999, features 32GB of GDDR7 memory, 21,760 CUDA cores, and a memory bandwidth of 1,792GB/sec.
It is said to be twice as fast as the RTX 4090, thanks to the new Blackwell architecture and DLSS 4 technology. The RTX 5090 will require a 1000-watt PSU and has a total graphics power of 575 watts.
The RTX 5080, priced at $999, offers 16GB of GDDR7 memory, 10,752 CUDA cores, and 960GB/sec of memory bandwidth.
Nvidia promises double the performance of the RTX 4080 with a power requirement of 850 watts.
The RTX 5070 Ti ($749) and RTX 5070 ($549) will also be part of the series, offering significant performance boosts over their predecessors.
The RTX 5070 Ti is expected to be 2x faster than the RTX 4070 Ti, while the RTX 5070 will deliver RTX 4090-level performance at a lower price.
Nvidia will also bring these GPUs to laptops starting in March, with versions featuring up to 24GB of GDDR7 memory.
The new DLSS 4 technology will enhance frame rates and image quality across supported games, with new features like Multi Frame Generation and real-time AI rendering.
The RTX 50-series GPUs are set to redefine gaming and content creation, offering a combination of power, efficiency, and cutting-edge AI technology for a variety of users.