GeForce RTX 4080 SUPER Review: Chasing RTX 4090, For Under $1K

	NVIDIA GeForce RTX 4080 SUPER: MSRP $999 The high-end GeForce RTX 4080 SUPER completes NVIDIA's SUPER trifecta, which enhances the performance and value proposition of its desktop GPU line-up.
	Great All-Around Performance Black Colorway Looks Awesome Relatively Cool & Quiet Higher Value Than Original 4080	Beefy Form Factor Only Slightly Faster Than 4080 Inferior (To AMD) Display Outputs

---

The final member of NVIDIA’s GeForce RTX 40 SUPER series trifecta launches today, the GeForce RTX 4080 SUPER. To date, we’ve already evaluated the GeForce RTX 4070 SUPER and RTX 4070 Ti SUPER, and found them both to offer increased performance over their respective predecessors, and more overall value thanks to reduced introductory prices. NVIDIA’s goal with the more powerful GeForce RTX 4080 SUPER is roughly the same. The RTX 4080 SUPER is amped up in a few ways versus the original and its introductory price is about 20% lower, for the Founders Edition model at least. Custom, hot-clocked partner boards with more bling will cost a bit more.

We’ve got a breakdown of the GeForce RTX 4080 SUPER’s main features and specifications below. We’ll go over how it differs from the original, offer a quick tour of this black beauty, and then get to what most of you probably came here for – some benchmarks...

NVIDIA GeForce RTX 4080 SUPER Specifications

---

Like its predecessor, the new GeForce RTX 4080 SUPER is built around NVIDIA’s AD103 GPU. In terms of feature support, the AD103 is identical to the AD102 powering the flagship RTX 4090 (and the more scaled down GPUs in the GeForce RTX 40 Series). The AD103 offers all of the features inherent to the Ada Lovelace architecture, including NVIDIA technologies like DLSS 3 with frame generation, along with other NVIDIA innovations like Reflex latency reduction, NVIDIA Broadcast, Ansel, G-SYNC, Omniverse, optional Studio drivers, hardware accelerated AV1 encoding, and GeForce Experience, to name just a few.

For a more detailed explanation of the Ada Lovelace GPU architecture, we suggest reading this article and checking out our launch coverage of the GeForce RTX 4090. Those two articles will explain what makes the GPU powering the GeForce RTX 4080 SUPER tick and we won’t be rehashing many of the architectural details here.


Versus the original GeForce RTX 4080, the AD103 on the RTX 4080 SUPER is scaled up in a few key ways. The AD103 powering the original GeForce RTX 4080 is outfitted with 7 GPCs, 38 TPCs, 9,728 CUDA cores, 304 Tensor cores, and 76 RT cores, with 64MB of L2 cache and a 256-bit memory interface. And the GDDR6X memory on the original 4080 runs at an effective 22.4Gbps data rate, which equates to nearly 717GB/s of peak memory bandwidth. The GeForce RTX 4080 SUPER, however, sports 7 GPCs, 40 TPCs, 10,240 CUDA cores, 320 Tensor cores, and 80 RT cores, also with 64MB of L2 cache and a 256-bit memory interface. The memory on the GeForce RTX 4080 SUPER is the fastest implementation of GDDR6X yet though, clocking in at an effective 23Gbps data rate, which works out to 736GB/s of peak memory bandwidth. The capacity remains the same at 16GB. The RTX 4080 SUPER's boost clock also ticks upward a bit to 2,550MHz, versus 2,505MHz on the original.

For reference, the AD102 on the RTX 4090 has 11 GPCs, 64 TPCs, 16,384 CUDA cores, 512 Tensor cores, and 128 RT cores, with a 384-bit memory interface. So, the GeForce RTX 4080 SUPER upgrades the original RTX 4080 with more cores and higher clocks, but the GeForce RTX 4090 is still going to reign supreme.

The NVIDIA GeForce RTX 4080 SUPER Founders Edition

When looking at the GeForce RTX 4080 SUPER, I hear the voice of Mr. Miyagi, “Different, but same.” The cooling solution on the GeForce RTX 4080 SUPER is physically similar to the original RTX 4080 in terms of its overall design and dimensions, but like the other cards in the RTX 40 SUPER series it is adorned in all black – which we think looks great, especially on this behemoth.

The GeForce RTX 4080 SUPER’s cooling solution features dual axial high-flow fans, a large vapor chamber, and a pass-through design like other Founders Edition boards. The pass-through cooler on the GeForce RTX 4080 SUPER is partially enabled by its dense, short PCB. The card might be big, but the PCB underneath is not.
One end of the heatsink assembly is attached to a vapor chamber, which is mounted directly to the GPU and memory. The fan above that section directs air through the heatsink and immediately funnels it out of the chassis through large vents in the RTX 4080 SUPER’s case bracket. The heatsink on the back half of the card, which is linked to the front vapor chamber via heat-pipes, allows air from the second fan to pass all the way through, where it is propelled upward and is eventually exhausted from a system, assuming it’s got proper ventilation (and depending on the mounting orientation).

The GeForce RTX 4080 SUPER measures in at 304mm (L) x 137mm (H) and requires 3-slots (61mm) – it is essentially identical in size to the RTX 4090 and original RTX 4080, but the all black color way gives it a distinct look. Upon first glance I thought, “This is Batman’s GPU.”

Like other 30 and 40-series Geforces, the RTX 4080 SUPER includes a power-dongle, which specifically requires three 8-pin PCI Express power feeds if you’re adapting a more common ATX PSU to work with the 12VHPWR connector on the card. The dongle isn’t necessary with an updated ATX 3.0 PSU equipped with a 12VHPWR.


For display connectivity, the GeForce RTX 4080 SUPER has triple full-sized DisplayPorts (1.4a) and a single HDMI 2.1 output, also similar to previous-gen cards.

And with that, let’s plug this puppy in and run some tests...