We don’t know much about the NVIDIA GeForce RTX 4000 series cards. Unfortunately, no one does at the time of writing this article.
However, there is some information we’ve managed to gather about this new generation of GPUs.
We also consider NVIDIA’s previous GPU lineup, the RTX 3000 series, and the performance improvements over the RTX 2000 series. This helps us visualize the potential of the RTX 4000 GPUs.
If you are interested in what the next generation of NVIDIA graphic cards will bring, this article contains the information you are looking for.
Let’s get right into it!
Updates +
- August 24, 2022: Updated specifications for the RTX 4090 Ti, 4090 and 4080.
- August 16, 2022: Added news that NVIDIA is pushing RTX 3000 sales to open up room for RTX 4000.
- August 11, 2022: Added news on reduced power draw and new specifications for the RTX 4080 and 4070.
- August 4, 2022: Added new release date information, new specifications and performance benchmarks.
- July 19, 2022: Added new release date information for the RTX 4000 cards.
- July 12, 2022: Added new information on possible delay of Ada Lovelace.
- July 5, 2022: Added updated information on SKU specifications.
- June 28, 2022: Replaced old power-consumption-related information with new leaks.
- June 24, 2022: Replaced a lot of outdated information.
- June 20, 2022: Added new release date rumors.
- June 14, 2022: Added new release dates, new power-related information on the RTX 4060 and more.
- June 7, 2022: Added power usage-related information, new release dates and reworked certain segments of the article.
- May 27, 2022: Added new information from Nvidia’s earnings call and cleaned up the article.
- May 17, 2022: Added a bunch of information on specification, release date, and more. Removed a bunch of outdated information.
- May 11, 2022: A couple of grammar fixes, no significant updates.
- May 4, 2022: Added and replaced a lot of information to coordinate with news that Ada Lovelace is on TSMC 5nm.
- April 22, 2022: Added new specification table, new power-related leaks and more.
- April 12, 2022: Added the possibility of Nvidia going with an RTX 5000 naming scheme.
- March 24, 2022: Updated information about Ada Lovelace’s potential power usage.
- March 15, 2022: Added power usage leaks for the RTX 4090.
- March 4, 2022: Added new release date, specifications leaks, L2 cache table, and a lot more.
- March 1, 2022: Minor information updates, nothing significant.
- February 22, 2022: Grammar updates.
- January 31, 2022: Added additional specifications leaks on the potential RTX 4090 Ti and more.
- January 25, 2022: Added information on RTX 3090 Ti and fixed some grammar issues.
- January 13, 2022: Added new specification-related leaks.
- December 22, 2021: Added a bit more information on RTX 3000 Super/Ti.
- December 14, 2021: A few updates, nothing notable.
- December 6, 2021: Added new information about RTX 40, TSMC, and the Metaverse.
- November 29, 2021: Reworked grammar throughout the entire article.
- November 22, 2021: Added a cleaner introduction.
- November 15, 2021: Added new release date information.
- November 12, 2021: Added performance leaks.
- November 3, 2021: Optimized readability.
- October 28, 2021: Reworked certain paragraphs for clarity.
- October 18, 2021: Added new information for the RTX 3090 Ti and updated some RTX 4000 related information.
- October 12, 2021: Added new information for RTX 3000 Super SKUs and RTX 4000 release date.
- October 4, 2021: Added specifications table for AD102 and other useful information.
- September 28, 2021: Made a few grammar corrections.
- September 20, 2021: Added more information regarding the release date.
- September 2, 2021: Added new leaks regarding the release date of Ada Lovelace.
Table of ContentsShow
Release Date

Currently, there is no official information regarding the release date of the following NVIDIA GPU lineup. So, what do we know so far?
Based on NVIDIA’s official architecture roadmap, Ampere Next (or Ada Lovelace) has a planned 2022 release. By 2024, they believe they will have Ampere Next Next ready, which is supposedly the RTX 5000 series.

There were several leaks about the release date of the RTX 4000 series, and most of them pointed towards Q3 or Q4 of 2022.
However, it seems that none of these leaks are now accurate.
Yes, only the AD102, and only one model.🤪
— Greymon55 (@greymon55) July 25, 2022
After several delay rumors, in the end, it seems that the only GPU NVIDIA will release in 2022 is an AD102 GPU (RTX 4090).
This is both unfortunate and unexpected. If AMD comes out with multiple SKUs in 2022, NVIDIA may have a hard time catching up with them.
NVIDIA also asked TSMC to cut down on orders for 5nm wafers. However, TSMC did not accept this agreement and only agreed to a one quarter delay on shipments which may be another reason why Nvidia is pushing for a 2023 release.
The company supposedly restarted the production of the 12GB RTX 3080, which means that the RTX 4000 launch is closer than ever. NVIDIA is trying to get rid of its Ampere stock as fast as possible to open up room for the next generation of GPUs.
Because there is too much stock of GA102, Nvidia has resumed the supply of 3080 12G.
— MEGAsizeGPU (@Zed__Wang) August 14, 2022
The 3080 12G just stopped production for less than two months, and recently resumed production quickly.
Note: Until RTX 4000 releases, RTX 3000 GPUs will continuously drop in pricing, making it a great time to get yourself a GPU.
NVIDIA’s Stopgap
To reduce the time gap between GPU releases NVIDIA had to introduce a stopgap. Something to create better competition against AMD’s lineup and to improve market share.
NVIDIA achieved this by releasing three new GPUs: RTX 3090 Ti, RTX 3080 Ti, and RTX 3070 Ti.
Even though these cards aren’t exactly a great upgrade over previous RTX 3000 GPUs, they are still a good option for anyone that can’t wait for RTX 4000 GPUs anymore.
Specifications

As mentioned previously, no official info is available for the RTX 4000 series, but there have been some leaks. Currently, the only concrete information is its codename: Ada Lovelace.
The Ada Lovelace microarchitecture will be on a 5nm fabrication process, a solid leap from the 8nm Ampere (Samsung) chips. A smaller microarchitecture will result in two significant benefits: more performance for a lot less power.
Thanks to TSMC’s 5nm process, Nivida gets those benefits by cramming more transistors onto the chip.
Note that most of the first leaks we had on the RTX 4000 suggested that Nvidia will use TSMC’s 5nm process.
GA102, AD102, AD103, and AD104 (rumored) specification comparison table:
Specifications | RTX 3090 | RTX 4090 Ti (The Beast) | RTX 4090 | RTX 4080 | RTX 4070 | RTX 4060 |
---|---|---|---|---|---|---|
GPU Die | GA102 | AD102 | AD102 | AD103 | AD104 | AD104 |
Process | Samsung 8nm | TSMC 5nm | TSMC 5nm | TSMC 5nm | TSMC 5nm | TSMC 5nm |
Base Clock Speed | 1395 MHz | ? | 2235 MHz | ? | 2310 MHz | ? |
Boost Clock Speed | 1695 MHz | ? | 2520 - 2750 MHz | ? | 2610 - 2800 MHz | ? |
CUDA Cores | 10496 | 18176 | 16384 | 9728 | 7680 | 4608 |
Streaming Processors | 82 | ? | 128 | 76 | 60 | ? |
Bus Width | 384-bit | 384-bit | 384-bit | 256-bit | 192-bit | 192-bit |
Memory | 24GB GDDR6X | 48GB GDDR6X | 24GB GDDR6X | 16GB GDDR6X | 12GB GDDR6X | 8GB GDDR6/X |
Memory Speed | 24Gbps | 24Gbps | 21Gbps | 23Gbps | 21Gbps | ? |
Bandwidth | 936.2 GB/s | ? | 1008 GB/s | 736 GB/s | 504 GB/s | ? |
L2 Cache | 6MB | 96MB | 96MB | 64MB | 48MB | 48MB |
Total Board Power | 350W | 800W? | 450W | 340W | 285W | 200W |
Release Date | September 1st, 2020 | TBA 2023 | October 2022 | Q4 2022? | TBA/Q4 2022 | TBA/2022/23 |
We’re basing the specifications in the table above based the latest leaks roaming the internet.
RTX 4090 Ti/The Beast
The leaks on NVIDIA’s “true” flagship are a bit vague. This AD102 chips that’s been referred to as the “The Beast” might be the 4090 Ti, Titan or maybe even get a completely different naming scheme.
Supposedly, this flagship SKU will have 12,432 CUDA cores, 48GB of GDDR6X running at 24 Gbps. Bandwidth will be well over one terabyte, considering that the regular 4090 will have a terabyte of bandwidth.
RTX 4090
If the RTX 4090 truly boosts up to 2520 MHz or even 2750 MHz, we might see some serious improvements in performance since the RTX 3090 boosts up to 1695 MHz. With AIB models, a 3000 MHz factory overclock is possible.
With a 60% improvement in boost clocks over its predecessor, NVIDIA might beat AMD’s RDNA 3 flagship SKU. But, this will come at a cost. With a 450W TDP and some of the highest clock speeds we’ve seen, we expect very high heat output.
RTX 4080
Unlike the 3080 (GA102), the RTX 4080 will be using the AD103 GPU die instead of AD102. So, the RTX 4090 and 4080 will not be sharing the same chip.
Newest leaks by kopite7kimi make the RTX 4080 considerably more compelling than it was a couple of months ago.
Let's make some updates.
— kopite7kimi (@kopite7kimi) August 23, 2022
RTX 4080
PG136/139-SKU360
AD103-300-A1
9728FP32
16GB 23Gbps GDDR6X
total card power 340W
Total card power is supposed to be around 340W (much more acceptable than 400W), memory speed is bumped up to 23Gbps, and bandwidth up to 736 GB/s.
RTX 4070
The RTX 4070 is where everyone’s focus should be, especially now with the newer specifications leaks from kopite7kimi.
There is an update of RTX 4070.
— kopite7kimi (@kopite7kimi) August 4, 2022
PG141-SKU331
7680FP32
12G 21Gbps GDDR6X
300W
TSE >11000
If the 4070 gets 12GB of GDDR6X VRAM @ 21Gbps instead of 10GB GDDR6 @ 19 Gbps (like previous leaks suggested), it could be as fast as the RTX 3090 Ti.
This performance estimate is supported by the leaks claiming that the 4070 will have a max boost of 2800 MHz and a boost clock of 2610 MHz, which is higher than the 4090 clock speeds.
The memory bus has also changed, from 160-bit to 192-bit. The power draw is still estimated at 285W, which might be the only downside for the RTX 4070.
L2 Cache
It seems that NVIDIA looks to increase L2 cache memory on all Ada Lovelace SKUs. Even the low-end GPUs (AD107) will get about 32MB of L2 cache. The RTX 4090 card will max out at 96MB of L2 cache.
The RTX 3060 has only 3MB of L2 memory, which means that the future RTX 4060 will have a ten times bigger L2 cache. To make this change even crazier, this means that the 4060 will have more L2 than the RTX 3090.
Here’s an L2 cache table comparing RTX 3000 and RTX 4000 GPUs:
RTX 3000 | L2 Cache | RTX 4000 | L2 Cache |
---|---|---|---|
GA102 | 6MB | AD102 | 96MB |
GA103 | 4MB | AD103 | 64MB |
GA104 | 4MB | AD104 | 64MB |
GA106 | 3MB | AD106 | 48MB |
GA107 | 2MB | AD107 | 32MB |
It looks like boosting cache size is a trend these days, considering that AMD and Intel increased their L2 and L3 cache sizes on their processors to boost gaming performance.
We’ll see whether Nvidia’s memory boost will improve the GPU’s ability to tackle games.
With these specifications in mind, it’s definitely possible that the RTX 4000 series graphics cards can be twice as fast as RTX 3000 cards. Maybe even faster.
TFLOPS
Allegedly, AD102’s target frequency is 2.2GHz, which is theoretically around 66 TFLOPS (FP32). That is almost double compared to Ampere’s flagship (RTX 3090).
However, Greymon55 has another say about the specifications of Ada Lovelaces, which counters 3DCenter’s rumors. In 2021, Greymon55 already posted a leak with AD102 specifications and mentioned that the 3090 successor could have up to 92 TFLOPS.
If lovelace gets up to 2.5GHz, you'll get about 90t of FP32, and 3090ti is just 40t.😬
— Greymon55 (@greymon55) January 25, 2022
Now, the leaker doubles down on the idea and still believes that AD102 will have up to 90 TFLOPS compared to the 66 TFLOPS rumored by 3DCenter. That’s double compared to the 3090 or even the 3090Ti.
However, remember that TFLOPS isn’t the most accurate depiction of in-game performance.
Performance
There are currently no benchmarks open to the public, so we can’t really determine the performance of the RTX 4000 series, but we have a few rumors to share.
Kopite7kimi revealed 3DMark Time Spy Extreme benchmarks with the RTX 4090, 4080, and 4070.
RTX 4080, TSE >15000,
RTX 4070, TSE ~10000.
These scores are based on specs I mentioned before.
Honestly, it's not quite sure yet except RTX 4090. Well, I don't care.— kopite7kimi (@kopite7kimi) July 29, 2022(Video) NVIDIA GeForce RTX 4000 - Release Date, Price, Specs | Everything You Need to Know
The RTX 4090 scores 19000 points in 3DMark, which is around 66% faster than the RTX 3090 Ti (~11400 points).
With 15000 points in Time Spy Extreme, the RTX 4080 is almost 25% faster than the 3090 Ti.
These kinds of performance jumps are expected, but what’s interesting is that the leak suggests that the RTX 4070 scores around 10000 points, making it almost as fast as a 3090 Ti.
It is also possible that this SKU might not be the real RTX 4070. The 4070 with 21Gbps will most probably be faster than the 3090 Ti.
This gives us an insight into the potential performance of Ada Lovelace, but don’t take these numbers as concrete evidence.
Originally, Greymon55 believed double performance for doubled power consumption and these benchmarks do point in that direction.
Double performance, double power consumption, can you accept it?
— Greymon55 (@greymon55) November 5, 2021
Will you accept 2x performance for such a high power draw?
Price
It is impossible to guess how the pricing will look with the current info. However, since AMD’s RX 6000 series is on par with the RTX 3000 series in terms of performance (in some cases even better), NVIDIA will most likely stick with the exact pricing as Ampere.
So, here’s what it should look like:
- RTX 4060 – $330
- RTX 4070 – $500
- RTX 4080 – $700
- RTX 4090 – $1500+?
However, this jump to TSMC’s 5nm process node could be the reason for far more expensive RTX 4000 GPUs
Scalping & Price Increases

Throughout the last couple of years, ever since the release of the RTX 3000 series, scalping has become a huge trend.
This new trend skyrocketed the prices of new GPUs while also considerably cut down the supply. This shortage continues in 2022 as it did in 2021 and 2020.
Even the world’s largest semiconductor manufacturers, TSMC and Samsung, struggle to keep up with the demand.
Right now, you might be wondering: will this kind of scalping affect the RTX 4000 series? Unfortunately, we cannot know for sure, but at least we know that both TSMC and Samsung are investing to improve their manufacturing capacities.
We’ll know the status of RTX 4000 availability once the GPUs are released.
Until then, you can check back for future developments on the RTX 4000 Series!
FAQs
How much is a RTX 4000? ›
Name | MSRP Price | 3DMark Score Value for Money |
---|---|---|
NVIDIA GeForce GTX Titan Black | $999 | 3 |
NVIDIA Quadro RTX 4000 | $899 | 8 |
NVIDIA Quadro P4000 | $815 | 5 |
NVIDIA Quadro M4000 | $791 | 2 |
With 15000 points in Time Spy Extreme, the RTX 4080 is almost 25% faster than the 3090 Ti. These kinds of performance jumps are expected, but what's interesting is that the leak suggests that the RTX 4070 scores around 10000 points, making it almost as fast as a 3090 Ti.
Is the RTX 4000 Series coming out? ›Nvidia GeForce RTX 40 series: Release date and price
Well-known leaker Greymon55 corroborated this by posting that the RTX 4000 cards could release in September of 2022.
That said, if pricing continues to hover around MSRP, the RTX 4080 could cost $699 USD, just like Nvidia's RTX 3080 should have at launch.
How much will the 4060 cost? ›Nvidia RTX 4060 price speculation
That said, if next-gen GPUs are available at MSRP, the RTX 4060 might come in at $329 USD, just like the RTX 3060. Naturally, gaming laptops wielding discrete variants of the chip will set you back more, but current pricing suggests you may be able to grab a one for around $1,300 USD.
The COVID-19 Pandemic and Inflation
Whether it's for work or for entertainment, lots of people are looking to buy electronic devices like computers, smartphones, or tablets. This has drastically increased the demand for graphics cards, which is why graphics cards are so expensive.
With that in mind, given that RTX 3000 GPUs launched in 2020, it's a safe bet that the company will release its new RTX 4000 pixel pushers in 2022. Rumours suggested that RTX 4000 was scheduled to be revealed in mid-July, but this may now have been delayed to September.
What is RTX do? ›NVIDIA RTX is the most advanced platform for ray tracing and AI technologies that are revolutionizing the ways we play and create. Over 150 top games and applications use RTX to deliver realistic graphics with incredibly fast performance or cutting-edge new AI features like NVIDIA DLSS and NVIDIA Broadcast.
What does ti mean in GPU? ›The abbreviation “Ti” means “Titanium” when seen in an NVIDIA GPU Name. Some examples include the 3080 Ti, 2080 Ti, 1080 Ti. It doesn't mean, however, that there is any Titanium used in the manufacturing of the GPU. At least not more than in any non-Ti cards.
What is the Next NVIDIA GPU? ›
Now the company is nearly ready to show its next generation of GPUs, the RTX 4000 series. NVIDIA confirmed during an earnings call that it will reveal its new architecture for consumer graphics cards next month, at the company's GTC 2022 keynote on September 20, 2022.
How many inches is the 3090? ›Length: 12.3 inches. Width: 5.4 inches. Height: 3-slot.
How much is the 4070 going to cost? ›We estimate the Nvidia RTX 4070 will be priced around $600, though there is no official pricing. Our estimate is based on Nvidia's previous pricing structure for the RTX 3070, which launched at $499.
How much better will the 4080 be than the 3080? ›NVIDIA RTX 4080 to be >70% Faster than the RTX 3080, RTX 4070 on Par with the RTX 3090 [Report] | Hardware Times.
When did RTX 4080 come out? ›The RTX 4080 is estimated to be released around November 2022. As Nvidia's next powerful graphics card, we've gathered up all of the rumors and leaks around the upcoming GPU so you won't need to look anywhere else for new information.
Is the RTX 4090 out? ›Nvidia GeForce RTX 4090 reportedly launching in October but it may not be the only RTX 40 GPU to come out in 2022.
How much VRAM will RTX 4090 have? ›The card also has 128 raytracing acceleration cores. NVIDIA has paired 24 GB GDDR6X memory with the GeForce RTX 4090, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 2235 MHz, which can be boosted up to 2520 MHz, memory is running at 1325 MHz (21.2 Gbps effective).
What is the latest GPU? ›The RTX 3080 is the best graphics card out there today. Well, the 10GB one is, at its original MSRP. You might find it going for a little more than that today, and don't forget the 12GB model that Nvidia later released, which is even more expensive still.
When can I expect my Nvidia 4000 series? ›With that in mind, given that RTX 3000 GPUs launched in 2020, it's a safe bet that the company will release its new RTX 4000 pixel pushers in 2022. Rumours suggested that RTX 4000 was scheduled to be revealed in mid-July, but this may now have been delayed to September.
Will GPU prices drop? ›Tom's notes that the overall GPU price drop since the start of 2022 is 57% on average, showing just how far price tags have come down in the first half of this year.
Why are GPUs so expensive? ›
The COVID-19 Pandemic and Inflation
Whether it's for work or for entertainment, lots of people are looking to buy electronic devices like computers, smartphones, or tablets. This has drastically increased the demand for graphics cards, which is why graphics cards are so expensive.
The Quadro RTX 4000 is an enthusiast-class professional graphics card by NVIDIA, launched on November 13th, 2018. Built on the 12 nm process, and based on the TU104 graphics processor, in its TU104-850-A1 variant, the card supports DirectX 12 Ultimate.