RTX 5090

RTX 5090 Specifications

The RTX 5090 is based on the Blackwell 2.0 architecture and manufactured using the 4 nm process node. It was launched approximately 3 months ago, originally priced at $1999. It features 21760 cores, including 170 compute units (SMs), 680 texture mapping units (TMUs), and 176 render output units (ROPs). For ray tracing and AI-accelerated tasks, it also includes 170 dedicated RT cores and 680 Tensor cores, enabling advanced rendering and upscaling features where supported. It has a base clock of 2017 MHz and a boost clock reaching up to 2407 MHz. The RTX 5090 comes equipped with 32 GB of GDDR7 memory across a 512-bit bus. Memory runs at 1750 MHz and delivers a total memory bandwidth of 1790 GB/s.

This GPU has a very high thermal design power (TDP) of 575 W. A PC case with excellent airflow and a high-quality, high-wattage power supply are essential for stable operation.

RTX 5090 Performance

RTX 5090 is an ultra high-end graphics card, achieving a relative gaming performance score of 100.00%. It serves as a reference point against which all other GPUs are compared in terms of performance. This GPU delivers unmatched 4K performance and is ideal for the most powerful and premium builds when paired with a high-end gaming CPU. Whether you're aiming for 300+ FPS in competitive titles at lower resolutions or 100+ FPS in AAA games at 4K with maximum visual fidelity, this is the GPU to get.

The gaming performance-per-price ratio of RTX 5090 is 22.4%, indicating lower value in this category. However, since this is a high-performance GPU, it remains a viable option for users who prioritize gaming performance and are less concerned about budget constraints.