There will be plenty of criticism for Nvidia’s new RTX 4080, but it’s important to stress that there’s nothing wrong with the Founders Edition we’re reviewing today in terms of its build, features, and overall quality. Like the RTX 4090, it’s a premium product created by an arguably industry-leading company that’s at the cutting edge of graphics technology. Pricing, however, is another matter. It’s way too high, even at its MSRP baseline, especially with some of the third-party partner cards we’ve seen. The product is a lot faster than any previous Nvidia Ampere product, including the RTX 3090 Ti, but the performance gains don’t always correlate to the price charged, so much so that there are data points that suggest the $1599 RTX 4090 actually offers a better deal .
The Founders Edition we see today comes in the same packaging as the RTX 4090 and in the same great case. The only difference is that while the card has the same controversial 12VHPWR socket (yes, the melting socket – we’re still waiting for a definitive answer on why this is happening), this time you get a Pin dongle adapter PCIe input. That’s still more than enough, bearing in mind that the same adapter comes with the much more power-hungry RTX 3090 Ti – and the RTX 4090 works with it too. The unified design of the two Ada Lovelace cards also means you get the same video options: one HDMI 2.1 and three DisplayPort 1.4a ports.
Since it’s a new generation of GPUs, both the RTX 4090 and RTX 4080 share some characteristics – despite using completely separate chips. This means Ada Lovelace’s enhanced video encoding options are preserved – faster h.264/HEVC encoding as well as dual AV1 encoders. Following the RTX 4090 review, we took a look at the capabilities of the AV1 – and it was impressive. For the high-quality videos we downloaded on digitalfoundry.net, we found that AV1 hardware encoding provides higher quality and saves a lot of files than software-based h.264, while software-based HEVC encoding provides smaller files, Nvidia AV1 delivers higher quality. For streamers and content creators, the RTX 4000 means a lot. Features like this should persist across all RTX 4000 lineups as newer and cheaper cards become available.
In the table below you’ll see how the RTX 4080 compares to its flagship partner, and it’s fair to say the cuts are substantial – wider and deeper than the spec differences we’ve seen between the RTX 3090 and RTX 3080. 59% more computing power, 73% more memory bandwidth, and two-thirds more VRAM. However, you’re paying 74% of the flagship’s cost price, so in reality you should expect at least 74% of the RTX 4090’s performance. Ideally, it should be more, because users expect cheaper products with better value for money.
Graphics card 4090 24GB | Graphics card 4080 16GB | RTX 4070 Ti (name pending) | |
---|---|---|---|
processor | AD102 | AD103 | AD104 |
transistor | 76.3B | 45.9B | 35.8B |
Die size | 608 square millimeters | 379 square millimeters | 295 square millimeters |
CUDA color | 16384 | 9728 | 7680 |
boost clock | 2.52GHz | 2.51GHz | 2.61GHz |
memory interface | 384 bits | 256 bits | 192 bits |
memory bandwidth | 1018GB/sec | 742GB/sec | 557GB/sec |
Three Gorges Project | 450W | 320W | 285W |
power supply recommendation | 850W | 750W | 700W |
power cable | 4 x 8-pin | 3 x 8-pin | 2 x 8-pin |
basic price | $1499/£1649 | $1199/£1269 | to be determined |
release date | October 12, 2022 | November 16, 2022 | to be determined |
You’ll notice that the above table includes figures for the “canceled” RTX 4080 12GB, which is based on a completely different Ada Lovelace processor and originally sold for $899. Its cancellation is actually more of a delay, as the card is being rebranded into a different line (our money is still on the RTX 4070 Ti), and it’s rumored to arrive in early January.
Before moving on to our roundup of gaming performance tests, let’s take a quick look at power efficiency. Going into this generation of graphics hardware, we’re bracing for extremely power-hungry devices in the coming energy crisis — and that might not be a good idea. Inaccurate rumors about a 900W RTX 4090 gave way to a 600W RTX 4090 and finally the actual TGP: 450W. This is still pretty powerful, but is actually less used in games. The power limit of the RTX 4080 is 320W, so in that respect it’s exactly the same as its predecessor, but what’s the reality in gaming?
Energy efficiency will vary greatly depending on the games you are running, of course if we add performance to power consumption – which is exactly what we do in the table below. In all cases, the RTX 4080 reported power consumption well below its 320W limit and had a considerable efficiency advantage over previous 80-class cards. In short, the frame rate has increased significantly from generation to generation, especially compared to the RTX 3080, and the performance advantage does not result in an increase in consumption. In fact, as you’ll see below, the RTX 4080 can deliver both performance gains and power savings in certain workloads.
GeForce RTX 2080 | GeForce RTX 3080 | GeForce RTX 4080 | Reduced power consumption per frame | |
---|---|---|---|---|
Control, 4K, High RT | 213W/17.2fps – 12.38 joules per frame | 309W/31.6fps – 9.78 joules per frame | 301W/44.66fps – 6.74 joules per frame | 45% vs. 2080/ 31% vs. 3080 |
Dying Light 2, 4K, Ultra RT | 193W/11.23fps – 17.19 joules per frame | 311W/25.3fps – 12.29 joules per frame | 290W/38.6fps – 7.51 joules per frame | 56% vs. 2080/ 39% vs. 3080 |
Forza Horizon 5, 4K, Extreme | 181W/47.7fps – 3.79 joules per frame | 290W/77.5fps – 3.74 joules per frame | 217W/118.0fps – 1.84 joules per frame | 52% vs. 2080/ 51% vs. 3080 |
All of this lays the groundwork for the plethora of benchmarks listed over the next six pages, covering standard rasterization in modern gaming, some of the most demanding ray tracing workloads we could put these cards through — and a look at today’s Advanced image reconstruction technologies (DLSS, FSR2) help mitigate the performance impact of the most challenging games.
Before we get into the numbers, here’s a brief overview of the new PCs we built to help test the new generation of GPUs. At the heart of our system is an Intel Core i9 12900K running at 5.2GHz with P cores and 3.9GHz with E cores. The CPU is augmented with 6000MT/s Trident Z5 RGB DDR5 memory from G-Skill. The Noctua NH-D15 is our go-to cooler for powerful processors while all games are run from the PCIe Gen 3 NVMe SSD. All components are mounted on an ASUS ROG Maximus Hero Z690 motherboard, while the power supply is powered by a Corsair RM1000i power supply.
Once you’ve finished your preliminaries, check out the table of contents below and see how the RTX 4080 compares to its closest Nvidia competitors, as well as AMD’s RX 6900 XT and RX 6800 XT. Note that after the release of the RTX 4090, Nvidia actually improved RTX 3000-class performance with driver updates. All RTX cards have been retuned to account for performance changes.
Nvidia GeForce RTX 4080 Analysis
- Introduction, Hardware and Power Analysis [This Page]
- RT Benchmarks: Dying Light 2, Cyberpunk 2077, Control, F1 22
- RT Benchmarks: Hitman 3, Metro Exodus Enhanced, Marvel’s Spider-Man Remastered
- RT/DLSS vs. FSR2 Benchmarks: Cyberpunk 2077, Dying Light 2, Marvel’s Spider-Man Remastered
- Gaming Benchmarks: Control, Cyberpunk 2077, Doom Eternal
- Gaming benchmarks: F1 22, Gears of War 5, Hitman 3
- Gaming benchmarks: Forza Horizon, Red Dead Redemption 2, Shadow of the Tomb Raider
- Nvidia GeForce RTX 4080: Digital Foundry Verdict