Nvidia GeForce RTX 4090 Review: Queen of the Castle
When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.
Editor’s Choice
(Image: © Tom’s Hardware)
Tom’s Hardware Verdict
The RTX 4090 delivers on the technological and performance fronts, easily besting previous generation offerings. With major enhancements to all the core hardware and significantly higher clock speeds, plus forward looking tech like DLSS 3, the new bar has been set very high — with an equally high price tag.
TODAY’S BEST DEALS
Pros
- +
Fastest GPU currently available
- +
Major architectural improvements
- +
DLSS 3 addresses CPU bottlenecks
- +
Excellent for content creation
- +
AV1 support and dual NVENC
Cons
- –
Extreme pricing and power
- –
Limited gains at 1440p and lower resolutions
- –
DLSS 3 adoption will take time
- –
We need to see AMD RDNA 3
- –
The inevitable RTX 4090 Ti looms
Why you can trust Tom’s Hardware
Our expert reviewers spend hours testing and comparing products and services so you can choose the best for you. Find out more about how we test.
The Nvidia GeForce RTX 4090 hype train has been building for most of 2022. After more than a year of extreme GPU prices and shortages, CEO Jensen Huang revealed key details at GTC 2022, with a price sure to make many cry out in despair. $1,599 for the top offering from Nvidia’s Ada Lovelace architecture? Actually, that’s only $100 more than the RTX 3090 at launch, and if the card can come anywhere near Nvidia’s claims of 2x–4x the performance of an RTX 3090 Ti, there will undoubtedly be people willing to pay it. The RTX 4090 now sits atop the GPU benchmarks hierarchy throne, at least at 1440p and 4K. For anyone who’s after the fastest possible GPU, never mind the price, it now ranks among the best graphics cards.
That’s not to say the RTX 4090 represents a good value, though that can get a bit subjective. Looking just at the FPS delivered by the various GPUs per dollar spent, it ranks dead last out of 68 GPUs from the past decade.
Except our standard ranking uses 1080p ultra performance, and the 4090 most decidedly is not a card designed to excel at 1080p. In fact, it’s so fast that CPU bottlenecks are still a concern even when gaming at 1440p ultra. Look at 4K performance and factor in ray tracing, and you could argue it’s possibly one of the best values — see what we mean about value being subjective?
Again, you’ll pay dearly for the privilege of owning an RTX 4090 card, as the base model RTX 4090 Founders Edition costs $1,599 and partner cards can push the price up to $1,999. But for those who want the best, or anyone with deep enough pockets that $2,000 isn’t a huge deal, this is the card you’ll want to get right now, and we’d be surprised to see anything surpass it in this generation, short of a future RTX 4090 Ti.
Swipe to scroll horizontally
| Graphics Card | RTX 4090 | RTX 3090 Ti | RTX 3090 | RTX 3080 Ti | RX 6950 XT | Arc A770 16GB | |
|---|---|---|---|---|---|---|---|
| Architecture | AD102 | GA102 | GA102 | GA102 | Navi 21 | ACM-G10 | |
| Process Technology | TSMC 4N | Samsung 8N | Samsung 8N | Samsung 8N | TSMC N7 | TSMC N6 | |
| Transistors (Billion) | 76. 2) |
608.4 | 628.4 | 628.4 | 628.4 | 519 | 406 |
| SMs / CUs / Xe-Cores | 128 | 84 | 82 | 80 | 80 | 32 | |
| GPU Shaders | 16384 | 10752 | 10496 | 10240 | 5120 | 4096 | |
| Tensor Cores | 512 | 336 | 328 | 320 | N/A | 512 | |
| Ray Tracing “Cores” | 128 | 84 | 82 | 80 | 80 | 32 | |
| Boost Clock (MHz) | 2520 | 1860 | 1695 | 1665 | 2310 | 2100 | |
| VRAM Speed (Gbps) | 21 | 21 | 19. 5 |
19 | 18 | 17.5 | |
| VRAM (GB) | 24 | 24 | 24 | 12 | 16 | 16 | |
| VRAM Bus Width | 384 | 384 | 384 | 384 | 256 | 256 | |
| L2 / Infinity Cache | 72 | 6 | 6 | 6 | 128 | 16 | |
| ROPs | 176 | 112 | 112 | 112 | 128 | 128 | |
| TMUs | 512 | 336 | 328 | 320 | 320 | 256 | |
| TFLOPS FP32 | 82. 6 |
40 | 35.6 | 34.1 | 23.7 | 17.2 | |
| TFLOPS FP16 (FP8/INT8) | 661 (1321) | 160 (320) | 142 (285) | 136 (273) | 47.4 | 138 (275) | |
| Bandwidth (GBps) | 1008 | 1008 | 936 | 912 | 576 | 560 | |
| TDP (watts) | 450 | 450 | 350 | 350 | 335 | 225 | |
| Launch Date | Oct 2022 | Mar 2022 | Sep 2020 | Jun 2021 | May 2022 | Oct 2022 | |
| Launch Price | $1,599 | $1,999 | $1,499 | $1,199 | $1,099 | $349 |
Here’s a look at the who’s who of the extreme performance graphics card world, with the fastest cards from Nvidia, AMD, and now Intel.
Obviously, Intel’s Arc A770 competes on a completely different playing field, but it’s still interesting to show how it stacks up on paper.
We’re going to simply refer you to our Nvidia Ada Lovelace Architectural deep dive if you want to learn about all the new technologies and changes made with the RTX 40-series. The above specs table tells a lot of what you need to know. Transistor counts have nearly tripled compared to Ampere; core counts on the RTX 4090 are 52% higher than the RTX 3090 Ti; GPU clock speeds are 35% faster, and the GDDR6X memory? It’s still mostly unchanged, except there’s now 12x more L2 cache to keep the GPU from having to request data from memory as often.
On paper, that gives the RTX 4090 just over double the compute performance of the RTX 3090 Ti, and there are definitely workloads where you’ll see exactly those sorts of gains. But under the hood, there are other changes that can further widen the gap.
Ray tracing once again gets a big emphasis, and three new technologies — Shader Execution Reordering (SER), Opacity Micro-Maps (OMM) and Displaced Micro-Meshes (DMM) — all offer potential improvements.
However, they also require developers to use them, which means existing games and engines won’t benefit.
Deep learning and AI workloads also stand to see massive generational improvements. Ada includes the FP8 Transformer Engine from Hopper h200, along with FP8 number format support. That means double the compute per Tensor core, for algorithms that can use FP8 instead of FP16, and up to four times the number-crunching prowess of the 3090 Ti.
One algorithm that can utilize the new Tensor cores — along with an improved Optical Flow Accelerator (OFA) — is DLSS 3. In fact, DLSS 3 requires an RTX 40-series graphics card, so earlier RTX cards won’t benefit. What does DLSS 3 do? It takes the current and previously rendered frames and generates an extra in-between frame to fill the gap. In some cases, it can nearly double the performance of DLSS 2. We’ll take a closer look at DLSS 3 later in this review.
From a professional perspective, particularly for anyone interested in deep learning, you can easily justify the cost of the RTX 4090 — time is money, and doubling or quadrupling throughput will definitely save time.
Content creators will find a lot to like and it’s a quick and easy upgrade from a 3090 or 3090 Ti to the 4090. We’ll look at ProViz performance as well.
But what about gamers? Unlike the RTX 3090 and 3090 Ti, Nvidia isn’t going on about how the RTX 4090 is designed for professionals. Yes, it will work great for such people, but it’s also part of the GeForce family, and Nvidia isn’t holding back on its gaming performance claims and comparisons. Maybe the past two years of cryptocurrency mining are to blame, though GPU mining is now unprofitable so at least gamers won’t have to fight miners for cards this round.
- MORE: Best Graphics Cards
- MORE: GPU Benchmarks and Hierarchy
- MORE: All Graphics Content
- Nvidia RTX 4090 at Amazon for $1,599.99
Nvidia RTX 4090: Price Comparison
15 Amazon customer reviews
☆☆☆☆☆
$1,599.
99
View
$1,599.99
View
$1,649
View
$1,667.32
View
$1,719.71
View
Show More Deals
powered by
- 1
Current page:
Meet the Nvidia GeForce RTX 4090
Next Page Nvidia GeForce RTX 4090 Founders Edition
Jarred Walton is a senior editor at Tom’s Hardware focusing on everything GPU. He has been working as a tech journalist since 2004, writing for AnandTech, Maximum PC, and PC Gamer. From the first S3 Virge ‘3D decelerators’ to today’s GPUs, Jarred keeps up with all the latest graphics trends and is the one to ask about game performance.
GeForce RTX 4090 Leaves Plenty of Room for a Future RTX 4090 Ti Flagship
When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.
(Image credit: Nvidia)
Nvidia’s GeForce RTX 4090 might look incredibly strong, and will certainly rank as the fastest option on our list of the best graphics cards when it debuts (at least until AMD’s RDNA 3 GPUs arrive), but the shaved down AD102 die in the RTX 4090 isn’t close to showing off the full potential of AD102 with all of its cores and cache enabled.
This combined with additional enhancements could hint at a future RTX 4090 Ti that will be much faster — and perhaps even more expensive.
The specs for the Nvidia RTX 40-series and Ada Lovelace GPUs, but those only show the announced and rumored cards. Nvidia’s full AD102 die comes equipped with 144 SMs, 18,432 CUDA cores, 96MB of L2 cache, and 192 ROPs. This translates to 12% more CUDA cores and a whopping 33% more L2 cache capacity compared to the RTX 4090 we have today. The fully enabled AD102 die also packs 9% more ROPS and 12% more Texture Mapping Units as well, thanks to the additional SMs.
But that’s not all that could be done for the future 4090 Ti. Micron has new 24Gbps GDDR6X memory modules in the works, another 14% boost over the RTX 4090’s 21Gbps modules, and still faster than the RTX 4080 16GB’s 22.4 Gbps modules that Nvidia claims are the fastest in the world right now. That would push the hypothetical (but very likely) RTX 4090 Ti up to 1152 MB/s of bandwidth.
But faster memory would come with higher power consumption, and we suspect that Nvidia is seriously holding back AD102’s full clock speed and power potential as well. All those rumors of 600W RTX 40-series graphics cards? We know Nvidia has successfully overclocked RTX 4090 to more than 3.0GHz, and that would definitely push up power use.
It looks like the Ada architecture and TSMC’s 4N process have plenty of headroom remaining beyond the RTX 4090’s 2520 MHz boost frequency. Once the process matures a bit more, and if Nvidia is willing to increase the power limits, we wouldn’t be surprised to see a RTX 4090 Ti clock at closer to 2800 MHz.
The theoretical performance of AD102 with all these bells and whistles enabled could reach a whopping 103 teraflops in FP32 workloads, and 826 teraflops in FP16 workloads with the Tensor cores, and 1652 teraflops with the Tensor cores in FP8 mode. That would be a huge 25% performance jump in comparison to the RTX 4090.
These gains would only be realized in GPU limited scenarios, of course, so probably not 1080p or 1440p gaming.
Heavy compute applications would also likely benefit. The combination of more L2 cache capacity, additional GDDR6X bandwidth, and more cores and clocks could result in tangible improvements.
Swipe to scroll horizontally
| Row 0 – Cell 0 | RTX 4090 Ti (Full AD102) | RTX 4090 | RTX 3090 Ti |
| Process | TSMC 4N | TSMC 4N | Samsung 8N |
| Transistors | 76.3B | 76.3B | 28.3 |
| SMs | 144 | 128 | 84 |
| GPU Cores | 18432 | 16384 | 10752 |
| Tensor Cores | 576 | 512 | 336 |
| Ray Tracing Cores | 144 | 128 | 84 |
| Boost Clock | 2800MHz??? | 2520MHz | 1860MHz |
| VRAM Speed | 24 Gbps? | 21 Gbps | 21Gbps |
| VRAM | 24GB | 24GB | 24GB |
| Bus Width | 384 | 384 | 384 |
| Memory Bandwidth | 1152GB/s | 1008GB/s | 1008GB/s |
| L2 Cache Capacity | 96MB | 72MB | None |
| ROPs | 192 | 176 | 112 |
| TMU | 576 | 512 | 336 |
| TFLOPS FP32 | 103. 2 |
82.6 | 40 |
| TFLOPS FP16 | 826 | 661 | N/A |
| TDP | 600W?? | 450W | 450W |
It appears Nvidia has a lot of performance headroom remaining with its GA102 die, with the potential to create a RTX 4090 Ti that could theoretically smoke the RTX 4090. It would certainly cost a lot more money, and consume way more power than a RTX 4090, but it can be done.
All of this will depend on how hard Nvidia wants to push its GA102 die, and that will almost certainly depend on how close AMD can come to matching Nvidia’s performance with the upcoming RDNA 3 chips. Yields on fully functional AD102 GPUs would also play a role, though it’s doubtful these would be high volume parts.
Nvidia could add some or all of these enhancements to an RTX 4090 Ti any time it feels the need.
We didn’t get the RTX 3090 Ti until 18 months after the RTX 3090 debut, but there were a lot of compounding factors in play. More likely is we’ll see a 2023 refresh of the RTX 40-series some time around nine months to 12 months after the initial salvo.
There’s also the rare chance Nvidia could skip the RTX 4090 Ti completely in favor of a new Titan variant, but we doubt that will be the case. Titan cards tend to cut into the lucrative RTX A-series professional card profits too much.
Join the experts who read Tom’s Hardware for the inside track on enthusiast PC tech news — and have for over 25 years. We’ll send breaking news and in-depth reviews of CPUs, GPUs, AI, maker hardware and more straight to your inbox.
Contact me with news and offers from other Future brandsReceive email from us on behalf of our trusted partners or sponsors
Aaron Klotz is a freelance writer for Tom’s Hardware US, covering news topics related to computer hardware such as CPUs, and graphics cards.
How to find out which video card is installed on your computer
All computers are equipped with graphics hardware that handles everything from desktop drawing, video decoding, to rendering demanding PC games. Most modern PCs have GPUs made by Intel, NVIDIA, or AMD.
While your computer’s processor and RAM play a big role when it comes to PC gaming, the GPU is usually the most important component. If you don’t have a powerful GPU, you won’t be able to play new PC games, or you’ll have to play them at lower graphic settings. Some computers have a low-power “built-in” or “integrated” graphics card, while others have powerful “dedicated” or “discrete” graphics cards (also called graphics cards).
In Windows 10, you can find GPU information and GPU load information right in Task Manager. Right-click on the taskbar and select “Task Manager” or press Windows+Esc to open it.
Click the “Performance” tab at the top of the window – if you don’t see the tab, click “More Information”.
Select “GPU 0” in the sidebar. The GPU manufacturer and model name will be displayed in the upper right corner of the window.
In this window, you will also see other information, such as the amount of allocated memory for the GPU. Windows 10 Task Manager also displays GPU load here and you can view GPU load by application.
If you have multiple GPUs installed on your system, each one will be displayed using a number corresponding to its physical location, such as “GPU 1”, “GPU 2” and so on.
On older versions of Windows, such as Windows 7, this information can be found in the Direct diagnostic tool. To open it, Press Windows+R, type “dxdiag” in the run dialog that appears, and press Enter.
Click the “Display” tab and look at the “Name” field in the “Device” section. Other statistics such as the amount of video memory (VRAM) built into your GPU are also listed here.
If you have multiple GPUs in your system—like a laptop with a low-powered Intel GPU for battery use, and a powerful NVIDIA GPU for use while plugged in and while gaming—you can control which GPU will be use the game using the Windows 10 Settings app.
These controls are also built into the NVIDIA Control Panel.
GPU – graphics card – graphics card – what’s the difference
There are two things we can say about GPUs, graphics cards and video cards: (1) they are the same, (2) they are different. Yes, this is not much to understand the issue, but I will try to explain further in the text.
What applies to graphics card, GPU and video card may vary depending on your level of knowledge (or the person you are talking to) and the situation you are in.
Let’s go back a little, here’s what’s true: GPU, graphics card and video card are not the same ! But, they are often used interchangeably, or means the same thing in a certain context.
When you go to a computer hardware store and ask an employee for a graphics card, you will get something like this: video card or even GPU. Store employees already know what people are looking for (often with less knowledge than they do) and don’t bother correcting them.
Now if you talk to an editor working on a feature film and tell her you just bought a new video card for gaming, she will be confused as to why you need a video card for gaming.
Let’s clear up the confusion:
What is GPU
GPU is short for “Graphics Processing Unit”.
A GPU consists of various logic circuits and so-called programmable cores .
Since the GPU chip itself cannot work without some kind of memory, power management and connection to your computer, it can be placed:
- Into the CPU
- On own PCB
When the GPU is embedded in the central processing unit (CPU), it is called iGPU – integrated graphics processor . The integrated GPU receives power management and communication with the rest of your PC hardware through the CPU.
It can also access and use system memory (RAM).
When the GPU is placed on its own PCB, it is called graphics card .
This brings us to:
What is a graphics card
Because a graphics card chip can’t do much without supporting hardware like memory or things like power management and cooling, it’s placed on a circuit board ( PCB), which has a place for these elements.
A graphics card is a printed circuit board that includes accessories such as VRAM (video memory) modules, power management, or cooling for the GPU and memory.
The
graphics card also has a high-speed connection, a PCIe connector that connects it to the motherboard to interface with the rest of your computer.
Graphic card on its own circuit board also called dedicated graphics card or dGPU (as opposed to iGPU – the integrated graphics processor inside the CPU).
The reason dedicated graphics cards exist is size and practicality .
Powerful equipment needs enough space, especially for the cooling system.
You don’t want your graphics card to overheat.
You can add multiple graphics cards to your PC if needed, upgrade the graphics card without necessarily changing anything else (such as the CPU if you want to upgrade the iGPU), and specialized graphics cards can be sold by specialized companies that focus in the production of the best video cards for specific tasks.
Typically, a graphics card is a specialized form of hardware that is really good at tasks that can be easily parallelized due to the many GPU cores.
Although graphics cards were originally designed for graphics or visual tasks, today they are used for any workload that can be easily parallelized.
What is a graphics card?0035
for video processing .
Since graphics cards such as Blackmagic’s or Elgato’s capture cards are fairly niche products, it’s forgivable to ignore them.
Video cards are specialized equipment that are very good at video processing.
Workloads such as video editing, conversion, movie projection, streaming, etc. need to process video streams, and the higher the resolution becomes or the higher the bit depth, the more performance you need.
Many videos have certain video codecs that cannot be encoded or decoded fast enough by the graphics card or processor.
Video cards designed by to encode, decode , capture and output very high quality video without slowing down the rest of your system.
What is the difference between GPU, graphics card and graphics card
GPU, graphics card and graphics card are interchangeable.
Although, to be exact , they mean different things.
- The GPU is the main chip of the graphics card.
- A graphics card is a fully functional piece of hardware (including a graphics processor) with a circuit board, video memory, and other accessory hardware.
- A video card is a special piece of hardware that speeds up video processing.
You will find that the distinction between these three hardware is rarely made.
Frequently Asked Questions
What is the difference between a graphics card and a graphics driver?
The graphics card is a physical piece of hardware designed to accelerate graphics.
The graphics driver is a “little” program that allows your operating system to use the graphics card. The graphics driver contains instructions on how to “control” the graphics card.
Is a video card important for PC video editing?
Depending on the complexity of your projects, a powerful video card can speed up many steps in video editing.
Software such as Premiere Pro and Davinci Resolve make good use of powerful graphics cards.
Which graphics card is better – NVIDIA or AMD?
Choosing the best graphics card depends on your workload.
Nvidia often leads the way in rendering and professional workloads, while AMD is considered the best deal, especially for gaming, in terms of performance per dollar.