There’s a growing problem with gaming PCs that no one is talking about. While it’s great to see GPUs getting more and more powerful with each generation and making gigantic leaps in performance from generation to generation, it comes at the expense of GPU size.
Graphics cards these days are absolutely massive, with some of them, like the RTX 3090, even coming with three-slot designs, forcing future PC builders to check whether the case they’re buying has enough space for it.
But what is driving this growth? And more importantly, will they continue to grow in future generations?
Why do GPUs have to be big in the first place?
We have to keep in mind that a GPU has many parts. It’s not just silicon – if it were just silicon, things would be much easier.
When you remove the shroud from a graphics card and reveal the underlying circuit board, you will find that it is roughly flat. The need for such a large shroud is actually twofold. On the one hand, to master the thermals of a GPU, you need a large heatsink capable of drawing heat away from the GPU die and the card. These large fans don’t do their job alone – they need to be aided by an equally large heatsink to do a decent job of cooling.
As you move up the performance chain, you’ll notice that it becomes increasingly difficult to find compact designs the higher-end a GPU is. This is because more powerful cards draw more electricity, and therefore more heat, which means more space is needed on the heatsink.
On the other hand, it also serves aesthetic purposes. A big part of what adds to GPU complexity is that OEMs like Asus, Gigabyte, or MSI like to add pizzazz and style to their GPU. They include things like RGB lights and other decorations in their premium offerings. Most computer cases these days come with an acrylic or glass window to show the inside, so you can just as well make your PC look great from the outside and inside. .
Why are GPUs getting bigger, then?
Remember how we mentioned that the higher-end a graphics card is, the harder it is to find compact versions of it because they put out more heat? Well, that’s basically it – high-end cards demand more power, and with each generation we find that newer GPUs require even more power than their direct predecessors.
Take the RTX 3080 Ti, for example. The power consumption of the board is rated at 350W. In contrast, its predecessor, the RTX 2080 Ti, pulls a more acceptable 250W. The power consumption of the non-Ti 3080 is 320W, while the 2080 only needs 215W. There was no RTX 2090 in the days of Turing, but the RTX 3090 Ti is designed for draw 450W of power. The Nvidia Titan RTX, the most powerful non-Quadro Turing card, is rated for 280W.
People are often advised to buy a 1000W power supply when buying a 3090 Ti, which is just insane, especially considering the cost of a high quality power supply over 1000W For other boards, you’re good with 850W or 750W capacity – they’re more affordable, but they’re still powerful, power-hungry PSUs.
The massive power of these Amp boards ultimately translates into heat. That’s why we’re seeing graphics cards coming in three-slot sizes. It needs a gargantuan heatsink and high quality fans to keep up.
Will graphics cards continue to get bigger in the future?
It’s too early to know for sure, at least at the time of writing. Most rumors say that the RTX 4000 series, which is expected to launch in late 2022, will benefit from a further increase in power consumption. Of course, this requires even more cooling, which the GPU maker will pass on to customers in the form of even larger graphics cards.
According to rumors collected by Hardware Times, the AD102 GPU die, based on the Lovelace architecture and said to provide the brains of the RTX 4080 and 4090, will have a power limit of 800W. The AD103, the likely GPU part of the RTX 4070, could draw up to 450W. increase power consumption again.
Expect to pick up both a big PC case and a powerful PSU if you’re planning on getting an RTX 4000 GPU. If you’re buying an RTX 4090, don’t be surprised if you need a power supply of 1000W or even 1200W. For low-end GPUs, however, you should be fine with 850W or 750W.
What can I do to get a smaller GPU?
There are ways to reduce the size, even on high-end GPUs like the RTX 3090, if you don’t mind messing with water cooling.
If you plan to install a water cooling loop and include your GPU in it, you will find that water blocks like EK reduce the overall thickness and size considerably. Depending on what you’re using, you might even be able to make it a single-slot GPU.
If you don’t feel like taking apart your GPU and installing a water block in it, you can also find AIO options. Companies like Asus, for example, will sell you a GPU with a water block connected to a heatsink and pump, similar to AIO coolers for CPUs.
Granted, if you go this route, you’ll need to make sure your PC can actually accommodate a heatsink (or two if you’re also using CPU water cooling). This option tends to be more expensive, as an AIO GPU can cost you an additional $200 or $300 compared to an air-cooled variant of the same GPU.
GPUs are bigger because they require more power
The main reason for the current situation is that new generations of GPUs require more power than ever. And until that’s fixed, we’ll have to live with graphics cards that get bigger day by day.
If you really must get a thinner video card, you’ll have to settle for a low-end GPU, like a 3060, or mess with water cooling.