NVIDIA GeForce RTX 5090 GPU Family Specifications

The NVIDIA GeForce RTX 5090 Founders Edition Video Card is incredibly well built, it's a marvel of engineering, and does offer the absolute best gameplay experience. It' provides playable performance at 4K, and allows Ray Tracing with Upscaling. It also supports DLSS 4 Multi Framegen, and Neural Shaders. It's expensive, and its value compared to the GeForce RTX 4090 it replaces is narrow, due to the performance uplift versus price increase. Overall, it gets you the best experience, but you'll be paying for it.

GPU Family Basics
GPU Manufacturer	NVIDIA
GPU Generation	RTX 50 Series
GPU Architecture Name	Blackwell
GPU Die Code	GB202
Default TGP	575 W
Launch Price	$1,999

GPU Family Memory
Default Memory Bandwidth	1791 GB/s
Default Memory Size	32 GB
Memory Bus Width	512 bit
Memory Type	GDDR7

GPU Family Chip Details
Transistors	92 billion
Die Size	744 mm^2
CUDA Cores	21760
RT Cores	170
ROPs	192
TMUs	680

GPU Family Clock Speeds
Default GPU Base Clock	2010 MHz
Default GPU Boost Clock	2410 MHz
Default Memory Clock	2.209 GHz

The GeForce RTX 5090 GPU — the fastest GeForce RTX GPU to date — features 92 billion transistors, providing over 3,352 trillion AI operations per second (TOPS) of computing power. Blackwell architecture innovations and DLSS 4 mean the GeForce RTX 5090 GPU outperforms the GeForce RTX 4090 GPU by up to 2x.