Nvidia announces 'the most powerful single slot GPU on the planet' but it's a workstation card so naturally costs $1,250

Nvidia RTX 4000 single-slot graphics card.
(Image credit: Nvidia)

At 6,144 CUDA cores, 20GB of GDDR6, and a 130W TDP, the RTX 4000 is "the most powerful single slot GPU on the planet" according to Nvidia. A tantalising glimpse of a genuinely slimline graphics cards—if you can look past the price.

Stuffed with an Ada Lovelace AD104 chip, the RTX 4000 delivers the same graphical architecture found inside the entire RTX 40-series GeForce lineup. It loosely slots in between the RTX 4070 and RTX 4070 Ti in the GeForce stack, though it's not an exact match for all its extra VRAM.

Extra VRAM but less bandwidth. This card comes with a 160-bit memory bus for 360GB/s overall. It's also a slimmer core count than the RTX 4000 mobile chip already found in workstation laptops, though this wouldn't be the first time Nvidia trimmed back the desktop version of a card. It's a match for the RTX 4000 SFF in many ways, though that compact card has much lower power demands.

What's actually appealing about the RTX 4000 is its single-slot shroud. Wrapped in a business-formal black and gold trim, the 12-pin power connector is hitched out of the way on the opposite end to the IO. It's gorgeous, and a form factor we've all but entirely lost save for a few ageing models and liquid-cooled blocks in PC gaming.

Granted, it's a blower-style design, which we see very few of in the gaming space nowadays—it just doesn't cut it for the monstrously powerful GPUs of today. There's a reason Nvidia can get away with such a cooler here, however, and that's because this thing is designed to run a lot lower wattage than a comparative GeForce card would. 

Compared to an RTX 4070 at 200W, this card only demands 130W. You can see how that hits the card's performance: it's rated to 26.7 TFLOPs, a reduction on the RTX 4070's 29.15 TFLOPs, and that's despite wielding more cores and sporting a higher memory capacity.

Your next upgrade

Nvidia RTX 4070 and RTX 3080 Founders Edition graphics cards

(Image credit: Future)

Best CPU for gaming: The top chips from Intel and AMD.
Best gaming motherboard: The right boards.
Best graphics card: Your perfect pixel-pusher awaits.
Best SSD for gaming: Get into the game ahead of the rest.

Sacrifices have clearly been made here for that diminutive form factor, but Nvidia would have it so you stack a load of these in a single machine to make up for its single-card performance. Let's say 4 x 1,250… that'll be $5,000 please.

In theory, any of these RTX cards could work for a spot of gaming. Their drivers aren't completely foreign to us. It's just those prices that make sure they'll remain enterprise-only.

The RTX 4000 is the cheapest of three new enterprise-grade graphics cards out of the green team. It launches this September, followed by the $2,250 RTX 4500 in October. The new RTX 5000—not to be confused with would-be next-gen 50-series GeForce cards—is out now for $4,000.

Jacob Ridley
Senior Hardware Editor

Jacob earned his first byline writing for his own tech blog. From there, he graduated to professionally breaking things as hardware writer at PCGamesN, and would go on to run the team as hardware editor. Since then he's joined PC Gamer's top staff as senior hardware editor, where he spends his days reporting on the latest developments in the technology and gaming industries and testing the newest PC components.