• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

Nvidia 5000 series rumoured release is 2025

Soldato
Joined
22 May 2010
Posts
12,235
Location
Minibotpc
Much more expensive is my guess.

And with AMD out of the high end market, can only imagine the 5080 and 5090 getting even more expensive. $100-$200 increase is my guess, i don't think any consumer in the right mind would purchase one tbh. They would rather stock just sit and rot rather than discounting it.

This is the feel i get from nvidia. AMD seems to announce prices, get a feel for the reaction then drop the prices at launch.
 
Soldato
Joined
7 Dec 2010
Posts
8,299
Location
Leeds
Techradar opinion on the last gen...


He hit the nail on the head with what he says... Welcome to a world of 10-15% gen-on-gen improvements for GPUS, it is not like we had not seen that before with CPUS and Intel especially and the silly power use for them to give us these tiny improvements.

Ohh well welcome to more software tricks soon that x2 x4 x5 the FPS counters and upscale from 360p meeh...
 
Soldato
Joined
7 Dec 2010
Posts
8,299
Location
Leeds
And with AMD out of the high end market, can only imagine the 5080 and 5090 getting even more expensive. $100-$200 increase is my guess, i don't think any consumer in the right mind would purchase one tbh. They would rather stock just sit and rot rather than discounting it.

This is the feel i get from nvidia. AMD seems to announce prices, get a feel for the reaction then drop the prices at launch.

BUT BUT... you will get DLSS4 then and no other GPU can use it apart from the 50 series... worth every penny of the increase in price for more software tricks and for sure heading for more power use too and even larger coolers that will look like a car radiators ... just to justify the price increase.

GPUS are already silly sized and they need to come back down in size and have safe power connectors again, we don't need cards that can break motherboards PCIE connectors with their weight and power connectors that can melt and cause a fire risk because of the silly power use forced threw them tiny connectors now.

Anyways we will see in time what the plan will be next gen, maybe explains why AMD are saying hey heads up no next gen high end GPUS next gen as the power use will be silly and the coolers required will make them not usable by many .. and we know how amazing AMDs FSR and software solutions are so they basically waved the white flag knowing what will happen and where is their fake frame gen tech too aka FSR3 ? It's going to be laughable for sure you wait.. same as DLSS3 really is too but DLSS3 at least has DLSS2 to fall on as there is some benefits to that and well FSR2 is quality wise terrible for such tech.

See you all 2025 on the review threads for 5090 and 5080 and DLSS4 that will be 10x faster than 4090 before (according to Nvidia, but real world will be well laughable compared to their numbers)...
 
Last edited:
Soldato
Joined
23 Apr 2010
Posts
11,890
Location
West Sussex
He hit the nail on the head with what he says... Welcome to a world of 10-15% gen-on-gen improvements for GPUS, it is not like we had not seen that before with CPUS and Intel especially and the silly power use for them to give us these tiny improvements.

Ohh well welcome to more software tricks soon that x2 x4 x5 the FPS counters and upscale from 360p meeh...

Somebody hit the nail on the head earlier in another thread. They mentioned the 1080Ti.

I was lucky to get a Titan XP (big pee, the first one) about a month after launch for £675. I had it so long and became so utterly bored of it I got a 2070. A down grade even.

I don't think Nvidia are going to want to make that mistake again. They always take away anything that cheats the odds on value. Like SLI for example, and two GTX 460 beating the 480 for 35% less and so on. It was the same when Intel ruled the CPU space and had no competition. Pathetic uptakes and was all very incremental.
 
Soldato
Joined
28 Sep 2014
Posts
3,466
Location
Scotland

2024 will be interesting year with Nvidia first MCM chip Blackwell GB100 and GB102 target data center with massive change in design struture so 2025 Blackwell gaming chips GB202, GB203, GB205, GB206 and GB207 could be MCM chips too.
 
Last edited:
Soldato
Joined
28 Sep 2014
Posts
3,466
Location
Scotland
Associate
Joined
31 Dec 2010
Posts
2,490
Location
Sussex

2024 will be interesting year with Nvidia first MCM chip Blackwell GB100 and GB102 target data center with massive change in design struture so 2025 Blackwell gaming chips GB202, GB203, GB205, GB206 and GB207 could be MCM chips too.
If the later two or even the bottom three are MCM, that would imply that Nvidia are rushing into MCM with all the caution of AMD (i.e. almost no caution at all).

Whatever I think of Nvidia, they seldom misstep and IMO going without monoliths at the bottom and especially lower end laptops would be very risky thing to do.
 
Caporegime
Joined
18 Oct 2002
Posts
39,459
Location
Ireland
If the later two or even the bottom three are MCM, that would imply that Nvidia are rushing into MCM with all the caution of AMD (i.e. almost no caution at all).
And how did amd 'rush unto it with no caution at all'? It was in the works from 2016, hardly a rush.
 
Last edited:
Associate
Joined
31 Dec 2010
Posts
2,490
Location
Sussex
And how did amd 'rush unto it with no caution at all'? It was in the works from 2016, hardly a rush.
Yes, but I still maintain that a far more cautious approach would have had two monoliths and a MCM. Or if they had been willing to go bigger (Navi31's GCD at ~300mm² is big), two MCM and two monoliths.

Most likely we will never know, but why was Navi32 so delayed? Packaging issues are as likely as any reason IMO.
 
Caporegime
Joined
18 Oct 2002
Posts
39,459
Location
Ireland
Yes, but I still maintain that a far more cautious approach would have had two monoliths and a MCM. Or if they had been willing to go bigger (Navi31's GCD at ~300mm² is big), two MCM and two monoliths.

Most likely we will never know, but why was Navi32 so delayed? Packaging issues are as likely as any reason IMO.

Was it delayed though? It came out 2 years after rdna 2, which seems about right these days.
 
Soldato
Joined
6 Feb 2019
Posts
17,865

2024 will be interesting year with Nvidia first MCM chip Blackwell GB100 and GB102 target data center with massive change in design struture so 2025 Blackwell gaming chips GB202, GB203, GB205, GB206 and GB207 could be MCM chips too.


Incorrect. The leaks clearly state MCM is for GB100 only, 200 is all monolithic. There won't be any MCM gaming GPUs in the Blackwell generation


What I do find interesting is that Nvidia would launch server GPUs first on new architecture an entire year before it lets gaming GPUs get the new architecture- ensuring that all silicon used to build new architecture GPUs is sold to corporations for mega profit for an entire year before gamers can get any


It's basically Apple's strategy - your new architecture is launched and sold at crazy prices and mass market products have to wait a full year before they can get the architecture, creating a constant performance gap between consumer products and industrial products. Now they just need AMD to do the same and we'll have entire new way to screw gamers, and based on the rumours that RX8000 GPUs will be mid range cards only, I'd say it sounds like AMD is following Nvidia's strategy too
 
Last edited:
Man of Honour
Joined
13 Oct 2006
Posts
91,744
Meh. This stuff this far out is almost never right. I will start getting excited in 18 months time.

Very little information gets out these days, not like the old days when game developers, etc. had access to the new architectures way in advance and so on.
 
  • Like
Reactions: TNA
Soldato
Joined
15 Oct 2019
Posts
11,920
Location
Uk
Yup that is what I heard. Next AMD round going to be mid range only.
Considering this gen everything below a 4090 is at least 25-30% slower on average then doesn’t that make it midrange already especially when the 4090 isn’t even using above 89% of the full 102 die and could easily replaced by an even faster card?
 
Soldato
Joined
28 Sep 2014
Posts
3,466
Location
Scotland
Incorrect. The leaks clearly state MCM is for GB100 only, 200 is all monolithic. There won't be any MCM gaming GPUs in the Blackwell generation


What I do find interesting is that Nvidia would launch server GPUs first on new architecture an entire year before it lets gaming GPUs get the new architecture- ensuring that all silicon used to build new architecture GPUs is sold to corporations for mega profit for an entire year before gamers can get any


It's basically Apple's strategy - your new architecture is launched and sold at crazy prices and mass market products have to wait a full year before they can get the architecture, creating a constant performance gap between consumer products and industrial products. Now they just need AMD to do the same and we'll have entire new way to screw gamers, and based on the rumours that RX8000 GPUs will be mid range cards only, I'd say it sounds like AMD is following Nvidia's strategy too
I think you are incorrect stated there wont be any Blackwell MCM gaming GPUs. Look at AMD Navi 31 and 32 was the first AMD high end gaming MCM GPUs and also Mi300 was the first AMD data center MCM GPU. Now we know Nvidia are now catch up AMD data center MCM GPU with Nvidia first MCM GPU Blackwell GB100 so Nvidia will need to catch up with Navi 31 MCM GPU design.

Blackwell will be mark the 3rd time Nvidia will use the same architecture in both data center and gaming since Pascal and Ampere.

I guess cut down GB102 was aimed sell to China and others will be cancelled now after US enforced A800 and RTX 4090 sales ban listed China and others regions.

Now we have some information on GB100 that it will have 10 Texture Processing Clusters, 8 Graphic Processing Clusters with 160 SM so mean it will have 20,480 CUDA cores but we now have some very interesting information on GB202 that it will have 12 Texture Processing Clusters, 8 Graphic Processing Clusters with 192 SM so it will have massive 24,576 CUDA cores compared to GB100's 20,480 CUDA cores. I think GB202 RT will have 192 4th generation RT cores because it has same numbers as 192 SM.

AD102 has 76.3 billion transisters on TSMC 4nm with 144 SM and 609mm2 die size that is slight smaller than GH100's 80 billion transisters with 132 SM and huge 814mm2 die on same TSMC 4nm process and also it has same 18,432 CUDA cores count as AD102.

So if you look at GB202 numbers, it look like a massive chip contain maybe 160 billion transistors and it could be bigger than GB100 or rough the same size but it did not make any sense that GB202 is a monolithic chip while GB100 is a MCM chip. I dont think you can shrink to fit on 3nm 609mm2 or 750mm2 die size. Look at AMD Mi300 for example it has 146 billion transistors with 1017mm2 die size total on TSMC 5nm.

Q3 2025 is a long time away for Blackwell gaming GPUs launch but interesting Nvidia will launch next generation data center X100 in Q2 2025 after Blackwell GB100 in Q2 2024 so I think I figured out the X architecture name will be Xanthopoulos as here is only 1 X long name on physicists names list.
 
Soldato
Joined
15 Oct 2019
Posts
11,920
Location
Uk
I think you are incorrect stated there wont be any Blackwell MCM gaming GPUs. Look at AMD Navi 31 and 32 was the first AMD high end gaming MCM GPUs and also Mi300 was the first AMD data center MCM GPU. Now we know Nvidia are now catch up AMD data center MCM GPU with Nvidia first MCM GPU Blackwell GB100 so Nvidia will need to catch up with Navi 31 MCM GPU design.
Nvidia don’t need to catch AMDs MCM up, they are miles ahead in both raster and RT and come with better features. Nvidia could probably release a 400mm2 3nm chip and still beat whatever AMD puts out.
 
Back
Top Bottom