Thursday, September 26th 2024

NVIDIA GeForce RTX 5090 and RTX 5080 Specifications Surface, Showing Larger SKU Segmentation

Thanks to the renowned NVIDIA hardware leaker kopite7Kimi on X, we are getting information about the final versions of NVIDIA's first upcoming wave of GeForce RTX 50 series "Blackwell" graphics cards. The two leaked GPUs are the GeForce RTX 5090 and RTX 5080, which now feature a more significant gap between xx80 and xx90 SKUs. For starters, we have the highest-end GeForce RTX 5090. NVIDIA has decided to use the GB202-300-A1 die and enabled 21,760 FP32 CUDA cores on this top-end model. Accompanying the massive 170 SM GPU configuration, the RTX 5090 has 32 GB of GDDR7 memory on a 512-bit bus, with each GDDR7 die running at 28 Gbps. This translates to 1,568 GB/s memory bandwidth. All of this is confined to a 600 W TGP.

When it comes to the GeForce RTX 5080, NVIDIA has decided to further separate its xx80 and xx90 SKUs. The RTX 5080 has 10,752 FP32 CUDA cores paired with 16 GB of GDDR7 memory on a 256-bit bus. With GDDR7 running at 28 Gbps, the memory bandwidth is also halved at 784 GB/s. This SKU uses a GB203-400-A1 die, which is designed to run within a 400 W TGP power envelope. For reference, the RTX 4090 has 68% more CUDA cores than the RTX 4080. The rumored RTX 5090 has around 102% more CUDA cores than the rumored RTX 5080, which means that NVIDIA is separating its top SKUs even more. We are curious to see at what price point NVIDIA places its upcoming GPUs so that we can compare generational updates and the difference between xx80 and xx90 models and their widened gaps.
Sources: kopite7kimi (RTX 5090), kopite7kimi (RTX 5080)
Add your own comment

181 Comments on NVIDIA GeForce RTX 5090 and RTX 5080 Specifications Surface, Showing Larger SKU Segmentation

#51
64K
Darmok N JaladJust look at the transistor counts we’re at these days. To gain significantly more performance, it costs a lot. It’s an exponential growth curve, where 15% more cores gets steeper with each generation. The only other way to gain is more clockspeed, but again, more clocks over more cores has the same exponential penalty. It’s why new products are slowing down. New nodes only fix this so much, and I get the feeling they can’t keep pace with the demands needed for “generational” performance gains.
We're just going to creep slowly forward at this point on the hardware side imo until there is a substitute for silicon which is being researched but I have no idea when the goal will be reached. It's been speculated with one material researched several years ago that the leap could be up to 5 times faster transistors and possibly up to 5 times less watts used. I hope it comes soon but who knows.
Posted on Reply
#52
GoldenX
So let's double down on the Ada tactics eh.

Zero hope of going out of 8GB hell on the mid range again.
Posted on Reply
#53
Jism
N3utro600W and 400W, that's a 150 (33%) and 80W (25%) increase compared to 4090 and 4080. They'd better offer performance uplift significantly higher than these % or it will be a flop
40% tops.
Posted on Reply
#54
64K
GoldenXSo let's double down on the Ada tactics eh.

Zero hope of going out of 8GB hell on the mid range again.
Nvidia left that behind starting with Ada. You are thinking about the entry level 4060 which is really a 4050 anyway.
Posted on Reply
#55
Nin
All I care about is how well it can render big bouncing boobs and fat jiggling thighs.
Posted on Reply
#56
Darmok N Jalad
NinAll I care about is how well it can render big bouncing boobs and fat jiggling thighs.
Flops Per Second.
Posted on Reply
#57
adilazimdegilx
With this specs, 5080 will mostly likely be a 4090 replacement for slightly cheaper price and 5090 will just be money grabber at 2500$+. The reason that they didnt cut it down and go for full 512bit + 32GB is very obviously to charge people for it. And that's the correct way for them to maximize their profits.
Since AMD wont compete at this performance range, Ti version may not even come. But who knows, maybe nvidia gets bored along the way. However, I think it would be a mistake for nvidia to put a product between these two. With this performance gap they can force people to buy the expensive card instead of going with xx80 class.
Posted on Reply
#58
x4it3n
dgianstefaniDefinitely 5080 Ti with memory/cuda somewhere in between this gen lol.

Assuming these rumours are accurate. I'd be surprised to see an xx90 with full memory bus/die. 4090 was quite cut down. I don't think they're going to jump straight to 600 W from 450 W.

My guess 500 W.

20,000 cores.
If the 5080 has 84 SM and the 5090 has 170 SM, I would not expect the 5080 Ti to have more than 120 SM, unless they release a 5090 Ti with the full 192 SM or slightly lower (2 to 4 less SM for maximizing yields and costs). Also the 5080 Ti would have a 384-bit bus but not 448-bit nor 512-bit.

170 SM and 512-bit @ 32Gbps GDDR7 bus seems too good to be true knowing that they were going for 162 SM and 448-bit @ 28Gbps not that long ago... but if priced around $1800 it will sell really well!
Posted on Reply
#59
igormp
64KNot with the 5090 as they've already said but with the 5080 I think they will. Why wouldn't they? AMD had a competitor for the 1080, 2080, 3080, 4080. When AMD says high end I think they are referring to the xx90 GPUs which a lot of people call high end but some call enthusiast.
Rumors point out to RDNA4 topping out at 7900xtx levels of performance, which already falls behind the 4090.
if the 5080 manages to beat the 4090, then AMD may compete with it. Otherwise, no.
Posted on Reply
#60
InVasMani
Darmok N JaladFlops Per Second.
Jiggles 2 Seconds.

Ironically that sounds like something you'd hear the strippers yell out in Sleeping Dogs along with something like $20 dollah hollah!! That game is satirical gift that keeps giving...and the intro theme will continue to bang and love you long time.
Posted on Reply
#61
Beginner Macro Device
x4it3nIf the 5080 has 84 SM and the 5090 has 170 SM, I would not expect the 5080 Ti to have
...been released.

5080 Super with ~90 SM and slightly better VRAM speed is a likely continuation (provided the 84 SM 5080 is a real thing).
Posted on Reply
#62
x4it3n
Beginner Macro Device...been released.

5080 Super with ~90 SM and slightly better VRAM speed is a likely continuation (provided the 84 SM 5080 is a real thing).
Tbh it will depend on competition and what AMD does with RDNA 5

But if the leak is true the gap between the 5080 -> 5090 will be even bigger than 4080 -> 4090 ! ~2x vs ~68%
Also the 5090 having a 512-bit bus would mean 2x more Memory Bandwidth vs 5080 too! Whereas the 4090 "only" has 40% more bandwidth than the 4080, that's a big difference knowing that 4K and RT/PT are definitely Memory Bandwidth bound.
Posted on Reply
#63
bonehead123
Well, don't worry about being able to buy ANY of these cards when they come out, cause my AI Buyer Bot thingy informed me last week that it had reached an agreement to buy all of them, everywhere, all the time, all at once, even before they are released to testers/reviewers or other NDA-bound folks, hahahaha :)

And in case you are wondering, it only cost me $718.9743 bazillion, just a drop in my proverbial (cash) bucket.....

I'll make back at least 100x that selling them off to scalpers, hoarders and other assorted ilk of the interwebz (but not you good folks here though) :D

Yea yea I know ya'll are sooooo disappointed, but hey, money talks & bullshit walks, so just deal with it....

1st come 1st served as they say !
Posted on Reply
#64
Beginner Macro Device
x4it3non competition
On... what?
x4it3nwhat AMD does with RDNA 5
Probably nothing serious. Nothing implies RDNA5 will be able to outperform 4090 so 5080 Ti is of huge unnecessarity.
Posted on Reply
#65
Ruru
S.T.A.R.S.
64KMight even go as high as $3,000 for the 5090 if it doesn't get cut down or cut down by much from the possible specs and they call it a Titan. Nvidia has done a Titan for $2,500 and $3,000 in the past. :eek:
3090 already practically replaced Titan with just being gaming branded.

I also wouldn't be surprised at all with a 3000USD price tag.
Posted on Reply
#66
Bwaze
People here are still expecting this to be gaming card release.

Nope. No way. Nvidia didn't become hottest share in market by selling gaming paraphernalia.

I expect Nvidia to clearly release RTX 5090, and to lesser extent RTX 5080 to home AI acceleration crowd. Data center revenue is up more than 150% compared to last year, and now represents vast majority of Nvidia's income, thanks to AI craze. "Gaming" cards will no longer be just "gaming", as is clear from the change of RTX logo that now includes this:



And I don't believe they have included "Powering Advanced AI" just because DLSS is technically what we already call AI (machine learned upscaling), or that you could accelerate upcoming NPCs with ChatGPT - like abilities of conversation.

These cards will be offered as "cheap" accelerators for smaller neural network servers and as tools for artists and content creators.

And their prices will reflect that they are tools for generating income, not playthings. I expect a 100% price hike, just like in the good old cryptomadness days.

But don't despair, lower end RTX 40x0 will still be offered alongside Blackwell for all those who still like to play with their computer.
Posted on Reply
#67
evernessince
BwazePeople here are still expecting this to be gaming card release.

Nope. No way. Nvidia didn't become hottest share in market by selling gaming paraphernalia.

I expect Nvidia to clearly release RTX 5090, and to lesser extent RTX 5080 to home AI acceleration crowd. Data center revenue is up more than 150% compared to last year, and now represents vast majority of Nvidia's income, thanks to AI craze. "Gaming" cards will no longer be just "gaming", as is clear from the change of RTX logo that now includes this:



And I don't believe they have included "Powering Advanced AI" just because DLSS is technically what we already call AI (machine learned upscaling), or that you could accelerate upcoming NPCs with ChatGPT - like abilities of conversation.

These cards will be offered as "cheap" accelerators for smaller neural network servers and as tools for artists and content creators.

And their prices will reflect that they are tools for generating income, not playthings. I expect a 100% price hike, just like in the good old cryptomadness days.

But don't despair, lower end RTX 40x0 will still be offered alongside Blackwell for all those who still like to play with their computer.
For the 5090, if it has a 512 bit bus I agree. That indicates a card targeted at AI / Professional workloads. 32GB of VRAM is a decent upgrade over the 4090 as well although not enough to encroach on Nvidia's more expensive products.

That's said I don't see AI enthusiasts buying the 5080 if the specs are right. 16GB of VRAM is too skimpy and it's core count is skimpy. Those people would be better off scooping up 4090s with 24GB of VRAM. 16GB of VRAM can barely fit the FLUX model in it but with 24GB you can do FLUX plus at least one LORA.
Posted on Reply
#68
Beginner Macro Device
evernessinceI don't see AI enthusiasts buying the 5080 if the specs are right
Yeah, it'll be a "premium" gaming solution.

Eh, if that doesn't change we ain't seeing full RT, not now, not ever.
Posted on Reply
#69
Bwaze
evernessinceFor the 5090, if it has a 512 bit bus I agree. That indicates a card targeted at AI / Professional workloads. 32GB of VRAM is a decent upgrade over the 4090 as well although not enough to encroach on Nvidia's more expensive products.

That's said I don't see AI enthusiasts buying the 5080 if the specs are right. 16GB of VRAM is too skimpy and it's core count is skimpy. Those people would be better off scooping up 4090s with 24GB of VRAM. 16GB of VRAM can barely fit the FLUX model in it but with 24GB you can do FLUX plus at least one LORA.
I have a hunch about RTX 5080 as well. Just like when Lovelace came out, suddenly RTX 3090, 3090 Ti weren't good enough for DLSS 3.0 frame generation because they lacked "fourth-generation Tensor cores". Nvidia will offer a lot of new shiny AI-oriented tools with Blackwell release that will run much faster on new hardware, or it will be specifically locked to Blackwell hardware - because older cards lack electrolytes newest generation AI acceleration magical cores.
Posted on Reply
#70
x4it3n
Beginner Macro DeviceOn... what?

Probably nothing serious. Nothing implies RDNA5 will be able to outperform 4090 so 5080 Ti is of huge unnecessarity.
RDNA 5 could be a real competitor since it will use a real MCM design with up to 3 chips on it, and it's aimed for High-End performance!
RDNA 4 high-end chips were having issues so they cancelled all of them and are going to sell Mainstream GPUs instead to make more money, but RDNA 5 is supposed to fix all those issues and be a real competitor to RTX 5090.
Posted on Reply
#71
64K
x4it3nRDNA 5 could be a real competitor since it will use a real MCM design with up to 3 chips on it, and it's aimed for High-End performance!
RDNA 4 high-end chips were having issues so they cancelled all of them and are going to sell Mainstream GPUs instead to make more money, but RDNA 5 is supposed to fix all those issues and be a real competitor to RTX 5090.
If AMD doesn't release a 5080 competitor then I'll eat my damn hat!

I don't actually own a hat though so that's not much of a promise but I just can't see it happening. If they have already designed midrange GPUs with a midrange memory bus width then what would hold them back?

I understand the issues with a big chip and competing there but to stop at a 5070 competitor just doesn't make sense to me.
Posted on Reply
#72
Minus Infinity
64KAgreed. There's inevitably going to be some salvage on the big chip that will have to be sold somehow.
Hopefully with 24GB.
Posted on Reply
#73
nguyen
October release maybe :cool:
Posted on Reply
#74
64K
nguyenOctober release maybe :cool:
Not a chance. The last word is that it will be CES so early January and that might only be the official announcement. I can't recall now.
Posted on Reply
#75
QUANTUMPHYSICS
I will get the 5090.
I have no doubt it will exceed my 4090 and my 3090.
I am just sad it'll cost $2000 on top of the cost of the new 15900k and the new motherboard for it.
Posted on Reply
Add your own comment
Oct 5th, 2024 05:41 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts