The memory specifications of the upcoming RTX 3090 and RTX 3080 Ampere cards have just been confirmed by Videocardz. According to Videocardz’s internal sources at Add-in-Board (AIB) Partners, it has been confirmed that the NVIDIA GeForce RTX 3090 will feature 24 GB of GDDR6X memory, while the GeForce RTX 3080 will initially launch with 10 GB of GDDR6X memory. There’s a huge difference between the RTX 3090 & the RTX 3080 when it comes to the VRAM capacity, but only these specs have been confirmed for now.
There is no word on any Ti Model, but the RTX 3090 appears to be the flagship GPU in the Ampere lineup, directly replacing TITAN. The RTX 3090 will feature the GA102-300-A1 GPU. The GA102-300-A1 GPU sports 5248 CUDA cores or 82 SMs, which is a 20% increase in cores over the RTX 2080 Ti. We don’t have any details on the TMU (texture mapping unit), ROP count (raster operations pipeline) and the clock speeds yet. Assuming the RTX 3090 comes with 24 GB of VRAM then we are looking at a 384-bit wide memory bus, and 1 TB/s of bandwidth. The memory speeds for both the RTX 3090 and 3080 cards are expected to be around 19 Gbps.
But it is important to note that Gaming and HPC GPU variants have different configurations, so we can’t take the GA102-300-A1 GPU die as a reference if the RTX 3090 is going to target both the consumer and the HPC/enterprise market. The GeForce RTX 3080 on the other hand has been confirmed to get 10 GB GDDR6X memory, which appears to less that the RTX 3090, but this could also mean that we might get an RTX 3080 SUPER variant GPU with 16 GB of VRAM in the future. These super cards might also come in 20 GB flavors but for now only 10 GB of memory has been confirmed.
There are chances that Nvidia will launch the RTX SUPER series next year though. The RTX 3080 will feature the GA102-200-KD-A1 GPU die, which is a cut-down SKU having the same 4352 CUDA cores as the RTX 2080 Ti with a total of 68 SMs. Assuming the memory is running at 19 Gbps across a 320-bit wide bus interface, we can expect a bandwidth of up to 760 GB/s.
Nvidia is using the high-end GA102 GPU for the RTX 3080 as well, which appears to be an upgrade over the previous TU104 core featured on the RTX 2080. This could also mean that the new Ampere card will have higher wattage requirements and thermals, and it will fall under the high-end enthusiast segment. The GeForce RTX 3070 is also expected to be announced along with these two high-end cards, but we don’t have any specs on this SKU yet.
NVIDIA’s flagship RTX 3090 graphics card was also pictured recently, and is a massive 3-slot GPU. This model appears to have the same irregular shaped PCB which was leaked before. My guess is that this is the reference Founders Edition graphics card sample.
3 slots. 2000$. pic.twitter.com/ZgKsPUQ1U4
— James (@GarnetSunset) August 21, 2020
NVIDIA’s upcoming RTX 3000 series Ampere cards are rumored to be built on the Samsung’s 8nm process node. Nvidia has also recently ceased the production of the RTX 20 series of GPUs to make room for the Ampere lineup. Nvidia is hosting a Geforce Special Event on September 1st, and we expect the company to announce the next-gen Ampere Gaming GPUs.
Stay tuned for more!
Hello, my name is NICK Richardson. I’m an avid PC and tech fan since the good old days of RIVA TNT2, and 3DFX interactive “Voodoo” gaming cards. I love playing mostly First-person shooters, and I’m a die-hard fan of this FPS genre, since the good ‘old Doom and Wolfenstein days.
MUSIC has always been my passion/roots, but I started gaming “casually” when I was young on Nvidia’s GeForce3 series of cards. I’m by no means an avid or a hardcore gamer though, but I just love stuff related to the PC, Games, and technology in general. I’ve been involved with many indie Metal bands worldwide, and have helped them promote their albums in record labels. I’m a very broad-minded down to earth guy. MUSIC is my inner expression, and soul.
Contact: Email
10GB still seems a bit less for such a high-end expensive GPU. Not much an upgrade over Turing though, at least the memory config.
Kkk 20 Percent but 24 gb memory is nvidia crazy or patetics
what ?
Holy massive power draw, Batman!
What a shame that negotiations reportedly broke down with TSMC whose manufacturing process produces far more efficient GPUs than Samsung does.
The cards are still going to be much efficient than before though, despite the 8nm process node IMO
I guess that’s why the new card doesn’t need a larger power connector and a triple-slot design. Oh, wait!
Reportedly this new compact 12-pin power connector will be mounted at a 90- degree angle. Two 8-pin connectors wouldn’t fit this way, that’s why they will be replaced by the new connector.
It doesn’t seem five minutes since Turing arrived so I may just skip Ampere altogether in the hope Nvidia gets its act together for the RTX 4000 series.
Im on the Titan X Maxwell so I’m upgrading to the 3090 when it launches
My titan X Maxwell died right before the warranty was up. Contacted ASus, they didn’t even sh*t on me. Got me a Vega 64, that died 6 weeks in, contacted sapphire they sent out a modified Vega 64 pro series card to replace. My votes in I’m sticking with AMD Not to mention the amount of nerfs That Titan X Maxwell went through.
I think My titan x dying was the best thing that ever happened to me, it sent me over to AMD and i’m loving those deep blacks and realistic colors, not that wash out bullsh*t colors from the result of nvidia’s compression in order to make their cards run faster. Built My lady a new computer and threw a 5600 xt in their card runs like a beast and have way more superior suite to run with. I just hope AMD stays the course instead of trying to compete with nvidia’s never ending glass ceiling.
The last AMD card I owned was the Fury Nano, I was impressed with how much power the card had for such a small form factor. Ive had my TitanX since launch and have had no problems with it. I would go AMD again if they were to beat NVIDIA on performance and ray tracing and I have to say NVIDIA seems scared of RDNA2 as they have pushed the Ampere GPU’s hard in the power department at 350 Watts. That and the fact that the 3080 card is on 102 die instead of 104 die like they used for all the 80 class cards starting with Kepler. Remember Kepler started the tradition of selling the 80 class GPUs on the 104 die which used to be the 60 class cards dies
Better prep now for that liver donation.
suck my c*ck shetvidia.
The 3080 should have been at the very least 12gb
If there is not an higher vram variant of the 3080 at affordable price i will also skip this gen
These cards will melt one after another. Can’t wait to see some fried eggs experiments on that huge backplate, “fueled” by the 100degree C VRAM’s!
LOL! People better save the money for a water cooled variant!
So a 3080 will be around 30% faster than 2080ti but cost more, draw more power and take 2 extra slots? That doesn’t sound like a good deal to me.
3080 ONLY 10GB? the 80 class card keep becoming more and more of a joke
3080 are becoming 70 class card at the price of 80ti cards
thx ngreedia
I have the 12gb Titan X Maxwell GPU so I will be upgrading to the 24gb 3090
Is this a joke?
If RTX 3080 has 10 GB for now, then I expect the 3070 and 3060 to get 6/8 GB VRAM at the max ? Damn WTF !
Don’t worry they’ll be at least 20% more expensive than 20×0. Hueng gotta get that summer house folks!
I think that it very much depends on AMD’s next-generation graphics cards’ performance and prices.
early adopters always get screwed, with an almost infinite backlog of games, its not that hard to wait for the sane refined versions, you will get better hardware and better games
My 1080ti from 2017 has 11 gb. WTF?
It’s a psychological thingie so people will upgrade to the Super variants. Or simply buy a 3090 from the start.
Nice trick Nvidia! nice!
i plan to use 20% max of my brand new 750w psu (for all my build) so good luck nvidia / amd.
That 24gb card sounds nice to have. But I don’t really want to build a whole new computer for it. The only game that comes to mind that I’d want to run on it is a maxed out Red Dead II *drool*
Indeed. The SUPER variants will also surely come next year packing higher/better specs than the non-Super SKUs. Nvidia needs to milk customers so this is going to happen.
Also, I think we might even get a Ti variant, who knows ? I think its not worth upgrading this year. I’m waiting for AMD’s Big Navi cards though, but I’m not expecting any miracles from the Red Team.
Have you noticed that till now we have got almost 20 leaks/rumors, and news articles on Ampere RTX GPUs, and not a single one on RDNA2 Big Navi, or even a glimpse on the BIG Navi ?
There is a lot more information about RDNA2 performance and architecture than on Nvidia Ampere. For example we know that that transistor density is 2.5x higher than in cards from 2017 on 16nm with equal power consumption. We know that 250mm of RDNA2 is equal to 12 TFLOPS. We know that max RT peformance is 95 Giga Ray/Triangle intersection (RTX 2080 TI have max 10 Giga Ray/Triangle intersection)
https://www.anandtech.com/show/15994/hot-chips-2020-live-blog-microsoft-xbox-series-x-system-architecture-600pm-pt
Sounds like the –70 model will only have 8GB… for the third generation in a row. I’m either waiting for an aib with extra or seeing if AMD will offer more vram on their equivalent cards.
Nvidia is straight up repugnant now, no cap.