If you want to play games on a PC, you’ll need a graphics card (GPU). From “Cyberpunk 2077” to “Red Dead Redemption 2” and “Palworld,” you’ll need video RAM from a GPU to make it happen. And on your search, you’ll encounter different monikers used to describe Nvidia’s top graphics card options. Some card names include a “Ti” such as the RTX 4060 Ti, so it helps to know what “Ti” actually means. It’s Titanium, by the way. However, that’s not the only term you’ll see.
With an Nvidia graphics card like the RTX 4060 Ti, or the RTX 5050, there’s another glaring abbreviation staring you in the face: RTX. What does “RTX” actually mean on an Nvidia graphics card? Does it refer to an exclusive form of technology, or is it just there to make the card seem more intimidating? RTX stands for Ray Tracing Texel eXtreme, and it does refer to a type of visual technology incorporated by Nvidia’s latest graphics cards. Understanding what RTX actually does behind the scenes and why it’s important, however, is not so easily explained.
What is Ray Tracing Texel eXtreme?
Before the latest RTX and 50 series GPUs, Nvidia used GTX as a moniker for its graphics cards. The Nvidia GTX series dominated between the early 2000s and 2010s. It stood for Giga Texel Shader eXtreme, which was the visual technology employed by that generation of cards. A texel is essentially a pixel in the context of textures and 3D models. It’s the smallest unit of measurement that makes up those visual elements. GTX cards allowed for “Giga” texels, or a billion texels, indicating the increased power of that series of graphics cards.
The RTX series swaps the focus to ray-tracing, which is achieved through RT cores, dedicated processing units in the GPU that simulate real-world lighting and effects to make games seem more realistic. It makes a difference. Switch 2 has 10x the graphical power of the original Switch thanks to a custom Nvidia GPU with RT cores. So, the “Ray Tracing Texel eXtreme” indicates the increased ray-tracing and texel processing power in the current generation.
You’ll also notice there’s no number referenced in that title, like “Giga.” It’s likely because Nvidia’s RTX cards, while excellent for graphics, can also handle a lot more than just games thanks to Tensor Cores. Because of these cores, RTX cards are also great in professional settings to help train AI models. Tensor Cores are dedicated processing units for deep learning and AI computations, in the same way that RT cores are dedicated to ray-tracing computations. Nvidia RTX cards include both.
What does any of this have to do with gaming?
Technically, the Tensor Cores don’t add much to gaming unless developers have explicitly dedicated game processes to using them. Games can still employ the extra power, but in a limited capacity compared to other core functions — DLSS takes advantage of them. The RT cores, and ray-tracing, however, are a completely different story. Ray-tracing allows games to show more realistic lighting and effects to simulate how light moves, reacts, or even looks in the real world. To achieve that, the cards need more processing power, in the form of RT cores. When you see a game with ray-tracing on versus ray-tracing off, you can instantly tell the difference.
The newer 50 series RTX cards also introduced upgraded tech for machine-learning and AI, including more powerful AI cores, mostly usable in creative software and development scenarios. That’s why it might not be beneficial to upgrade when comparing the RTX 5050 versus the RTX 4060. That’s not to say the new cards aren’t more powerful overall, they are. But if you’re comparing the price difference to the performance boost, sometimes it’s better to wait.
