Review Nvidia GeForce RTX 5090 Founders Edition review: Blackwell commences its reign with a few stumbles

[Roland Of Gilead]

Great review @JarredWaltonGPU, as always.

Anyway, initial testing out of the way, I'm now poking at MFG and DLSS 4 stuff to try to determine what is and isn't a good experience. Stay tuned... that page six needs a lot of additional testing and data! 🙃

Is there any plan to cover DLSS 4 goodness with the older gen RTX20/30/40 series? With the new transformer model, could we expect both an increase in FPS + Quality at each setting? (Quality, Balanced, Performance etc). I expect that's possibly WAY down the list of priorities, but given this is the first time nVidia have done this with cards from the RTX era, it might be worth a look.

I look forward to the review being filled out further! 👍

 

[JarredWaltonGPU]

Great review @JarredWaltonGPU, as always.


Is there any plan to cover DLSS 4 goodness with the older gen RTX20/30/40 series? With the new transformer model, could we expect both an increase in FPS + Quality at each setting? (Quality, Balanced, Performance etc). I expect that's possibly WAY down the list of priorities, but given this is the first time nVidia have done this with cards from the RTX era, it might be worth a look.

I look forward to the review being filled out further! 👍

Yes, there's a plan. The plan is to finish testing 5090, poke at 4090 with the new DLSS stuff, get some numbers. Also try to run 3090. And then there's the 5080 that launches alongside the 5090 on the 30th, which means FE reviews can go up the 29th AFAIK.

I'm doing my best, even if Nvidia is trying to kill me! 🙃

What I need is someone like me, with an identical setup, to help test this stuff. And by "like me" I mean someone who not only knows what needs to be done but will do it properly. There are so many people that *should* be able to do this, but then when you try to teach them you discover that they're missing all sorts of important bits and bobs.

 

[saunupe1911]

The price/performance ratio is the same for both ... , so it is your $400 difference , pay it or save it. both are great cards.

I've had a 4090 FE for retail for a while now but was just asking based on what we know about the 5000 series. A 4090 at MSRP is looking pretty good right now.

 

[Thunder64]

Great review @JarredWaltonGPU, as always.


Is there any plan to cover DLSS 4 goodness with the older gen RTX20/30/40 series? With the new transformer model, could we expect both an increase in FPS + Quality at each setting? (Quality, Balanced, Performance etc). I expect that's possibly WAY down the list of priorities, but given this is the first time nVidia have done this with cards from the RTX era, it might be worth a look.

I look forward to the review being filled out further! 👍

My understanding is that the transformer model is more computationally intense which results in increased quality at a loss of FPS.

 

[Gaidax]

My understanding is that the transformer model is more computationally intense which results in increased quality at a loss of FPS.

I'm most certainly waiting for DLSS review deep dive, on the base level it is clear that what you say is what is happening.

But what I wonder is image quality/artifacts comparison between Performance/Balanced and Quality modes, because maybe now using Balanced/Performance modes would result in better image quality than DLSS2 at Quality mode had - which should be a performance increase while keeping up the good reproduction quality.

 

[redgarl]

If you look, I do a lot of non-gaming tests as well. Yes, gaming is a big focus, but it's not the only focus. And I also have to consider the fact that, barring a 5090 Ti or Blackwell Titan, this will undoubtedly be the fastest GPU around for the next two years. How can the fastest cards around with new features that will probably be sold out warrant a 3-star score (as someone else suggested)? That's ludicrous to me.

This is an amazing piece of hardware, even if it's not 50% faster than the 4090 in every scenario. And that performance right now is clearly a product of early drivers. These are literally the first public (ish) drivers for 5090. Nvidia internally can't test everything, and bugs and issues will slip through. The 9800X3D vs 13900K results prove how messed up things can be at times. Do I dock half a star for what will inevitably be a relatively fleeting problem? Again, I don't think that's warranted.

(Intel's driver problems are a different story, because we've seen the same things again and again for over two years. New games come out, we get some oddities. But the 4090 and 4080 Super worked fine with these drivers and it was only Blackwell having issues, and not even consistently so. I anticipate fixes will come in the next month or so.)

As you properly point out, value when you're looking at this sort of hardware is incredibly subjective. If you ONLY care about games, with zero interest in AI? Sure, it's probably a 3.5-star card because it's very expensive for relatively minor performance gains. More heavy RT testing will show larger gains, though, and that's what I'm currently working on doing.

Framegen and MFG are going to be very subjective as well. My personal experience with framegen is that you need a base framerate of 40~45 for it to feel "good" — meaning 80~90 FPS after framegen (and without framegen you'd probably be getting 55~65 FPS because FG only adds ~50% on Nvidia). If that same rule of thumb applies, we'll need MFG to provide 160~180 FPS, which means you'll want a 240 Hz display for it to be "useful," even on lower tier 50-series GPUs. I don't think a 5070 is going to do 4K at 160+ FPS without performance mode upscaling, though... but DLSS Transformers maybe makes that less of a concern.

Anyway, initial testing out of the way, I'm now poking at MFG and DLSS 4 stuff to try to determine what is and isn't a good experience. Stay tuned... that page six needs a lot of additional testing and data! 🙃

Worst Generational uplift.... EVER...
Highest MSRP... EVER...
Biggest Power Draw... EVER...

4.5/5

 

[Gaidax]

Man, reviewers sure have it hard dealing with all this fanboi/hater subjective crap. "Why did you give X score instead of Y score" cringe.

People can make their own decisions based on the review. Decide for yourself and stop trying to be this cringe content police.

 

[Thunder64]

Man, reviewers sure have it hard dealing with all this fanboi/hater subjective crap. "Why did you give X score instead of Y score" cringe.

People can make their own decisions based on the review. Decide for yourself and stop trying to be this cringe content police.

It's OK to disagree with a ranking. Seeing this is still a review in progress I think it is premature to give it a rank, let alone such a high one.

 

[redgarl]

Yes, there's a plan. The plan is to finish testing 5090, poke at 4090 with the new DLSS stuff, get some numbers. Also try to run 3090. And then there's the 5080 that launches alongside the 5090 on the 30th, which means FE reviews can go up the 29th AFAIK.

I'm doing my best, even if Nvidia is trying to kill me! 🙃

What I need is someone like me, with an identical setup, to help test this stuff. And by "like me" I mean someone who not only knows what needs to be done but will do it properly. There are so many people that *should* be able to do this, but then when you try to teach them you discover that they're missing all sorts of important bits and bobs.

Review and numbers are fine, your conclusion and your opinion, not so much.

If you can't even analyze your own numbers above your own excitement, then you are not a good reviewer...

Numbers and historical data don't lie. This is the worst gaming GPU Nvidia ever created... and this is undeniable.

But, you know... 4.5/5

ROFL

 

[mhmarefat]

Man, reviewers sure have it hard dealing with all this fanboi/hater subjective crap. "Why did you give X score instead of Y score" cringe.

People can make their own decisions based on the review. Decide for yourself and stop trying to be this cringe content police.

No, people value Tom's rating, that is why they are complaining about 4.5/5. They expect more from Tom's Hardware, to its reviews not be affected by marketing, hype, corporate lunacy, etc...

If people didn't complain, that would mean they do not value TH's review rating. And I fear with the current path TH is taking (same path as Nvidia, out of touch with reality of people's lives) many would lose their respect for this website.

It is because they CARE.

 

[Gaidax]

It's OK to disagree with a ranking. Seeing this is still a review in progress I think it is premature to give it a rank, let alone such a high one.

It's okay to disagree, it's not okay to be obnoxious or ridicule like that post you liked above.

In the end of the day each and everyone has their own values system including the person reviewing this in question. Score is a subjective number based on what said person wants and likes. Your mileage may vary, and it is okay, both ways.

And on top of that - there is a lot of actual hard objective numbers in that review too that took days to produce. Sitting here nitpicking what amounts to 1% of the review because of subjective reasons is simply cringe.

 

[helper800]

It is having power management issue, and overheating your PC Case because of the power output. Not to mention

Worst Generational uplift.... EVER...
Highest MSRP... EVER...
Biggest Power Draw... EVER...

4.5/5

And none of that means anything unless you include:
Highest performance consumer card... EVER...

 

[Gaidax]

No, people value Tom's rating, that is why they are complaining about 4.5/5. They expect more from Tom's Hardware, to its reviews not be affected by marketing, hype, corporate lunacy, etc...

If people didn't complain, that would mean they do not value TH's review rating. And I fear with the current path TH is taking (same path as Nvidia, out of touch with reality of people's lives) many would lose their respect for this website.

It is because they CARE.

People don't give a damn about whatever you wrote, let's not be coy about it.

They are mad he slapped 4.5 score on a $2k card that is out of their reach and that's about it. They want him to fight their wars against the bad Nvidia.

But, does that make that card not be the most powerful gaming GPU in existence by a mile or that 2 slot cooler keeping up 600w intake? No, it does not. So, it is what it is.

 

[Thunder64]

And none of that means anything unless you include:
Highest performance consumer card... EVER...

So then every new generation should get a high rating by deafult?

 

[Thunder64]

They are mad he slapped 4.5 score on a $2k card that is out of their reach and that's about it. They want him to fight their wars against the bad Nvidia.

That's a straw man. It is a rather weak gen over gen upgrade. Power use is way up. Drivers are incomplete. Saying that people think they don't agree with the rating because they can't afford it is disingenious. I'd bet many here don't want it even if they can afford it. Hence why people are asking if they should just get 4090's instead.

 

[helper800]

Review and numbers are fine, your conclusion and your opinion, not so much.

If you can't even analyze your own numbers above your own excitement, then you are not a good reviewer...

Numbers and historical data don't lie.

Nonsense.

This is the worst gaming GPU Nvidia ever created... and this is undeniable.

Opinions are 100% subjective built off a review of facts and Jarred's opinions are based on that set of objective facts. It seems to me that your opinion is simple. Power=high, cost=high, uplift=low, so therefore Nvidia BAD.

 

[mhmarefat]

People don't give a damn about whatever you wrote

Only an out of touch Nvidia fan would defend an out of touch 4.5/5 rating and simply ignore 6 pages of people's discussions. Go read what people have said in past pages.

 

[Gaidax]

That's a straw man. It is a rather weak gen over gen upgrade. Power use is way up. Drivers are incomplete. Saying that people think they don't agree with the rating because they can't afford it is disingenious. I'd bet many here don't want it even if they can afford it. Hence why people are asking if they should just get 4090's instead.

There is merit in claiming it's weak gen-to-gen increase - it is. But that is a 5090 review, not Blackwell review.

As a product, it still manages to outdo predecessor by ~30% FPS give or take at 4k.

This is still the most powerful commercially available gaming GPU in the world. You're not taking that from it and raw performance IS a key metric in these reviews.

 

[helper800]

So then every new generation should get a high rating by deafult?

The 5090 being 27% faster than the 4090 which was already 60% faster than the 3090 is not bad, just below expectations set from the 4090.

If you give context to the whole review with what was simplified, that could be an objective conclusion with the 5090, yes.

 

[Thunder64]

There is merit in claiming it's weak gen-to-gen increase - it is. But that is a 5090 review, not Blackwell review.

As a product, it still manages to outdo predecessor by ~30% FPS give or take at 4k.

This is still the most powerful commercially available gaming GPU in the world. You're not taking that from it and raw performance IS a key metric in these reviews.

Why would I want to take that from them? They made some gains and good for them. I just want to see some fairness. AMD's RDNA3 slides were crapped on and rightfully so. Outside of GN I haven't seen anyone critize Nvidia's marketing.

 

[DrunkenFerret]

Something I haven't seen mentioned yet is the fact that current-gen gaming CPUs may actually be holding back the RTX 5090, but not the RTX 4090, at least not in any noticeable way.

The TomsHardware GPU testing rig currently in use features an AMD 9800X3D, which is an excellent gaming CPU, but there’s an interesting point to consider when it comes to memory bandwidth. Based on AIDA64 benchmarks, with DDR5 6000 dual-channel RAM, the 9800X3D shows a read speed of around 62 GB/s, a write speed of 84 GB/s, and a copy speed of 59 GB/s.

For PCIe 4.0 x16, which maxes out at 32 GB/s unidirectional and 64 GB/s bi-directional, this isn’t really an issue. The available system memory bandwidth is comfortably above what the PCIe bus can handle, meaning there’s little to no risk of a bottleneck between the PCIe controller and the system memory. The CPU and memory can keep up with the data demands without any major slowdowns.

However, things start to look a little different when you consider PCIe 5.0 x16, which doubles the bandwidth to 64 GB/s unidirectional and 128 GB/s bi-directional. With PCIe 5.0 pushing such high data rates, there's a possibility that the memory subsystem may become a limiting factor.

If the GPU is trying to fully saturate the PCIe 5.0 link, the RAM's read and copy speeds might struggle to keep up, potentially causing a bottleneck between the PCIe controller and the system memory. This could lead to situations where the 5090 isn't able to fully stretch its legs, particularly in scenarios involving high data throughput.

In contrast, the 4090, running on PCIe 4.0, wouldn't face the same challenge because the available system memory bandwidth is nearly equal to what the GPU can demand via the PCIe bus.

What do you all think? Could the memory bandwidth limitations of the 9800X3D be a contributing factor here? Do you think that the 5090 might eke out a few more points if paired with a system with higher RAM bandwidths? Would love to hear others' thoughts on this.

 

[Gaidax]

Why would I want to take that from them? They made some gains and good for them. I just want to see some fairness. AMD's RDNA3 slides were crapped on and rightfully so. Outside of GN I haven't seen anyone critize Nvidia's marketing.

??????

 

[newtechldtech]

The 5090 being 27% faster than the 4090 which was already 60% faster than the 3090 is not bad, just below expectations set from the 4090.

If you give context to the whole review with what was simplified, that could be an objective conclusion with the 5090, yes.

5090 is actually 4090 ti renamed . the 27% increase is just 30% of more transistor counts. no generational leap here.

 

[helper800]

5090 is actually 4090 ti renamed . the 27% increase is just 30% of more transistor counts. no generational leap here.

Ada Lovelace and Blackwell architectures are distinctly different. The main similarity is that they are made using a similar process node.

 

[JarredWaltonGPU]

I'm most certainly waiting for DLSS review deep dive, on the base level it is clear that what you say is what is happening.

But what I wonder is image quality/artifacts comparison between Performance/Balanced and Quality modes, because maybe now using Balanced/Performance modes would result in better image quality than DLSS2 at Quality mode had - which should be a performance increase while keeping up the good reproduction quality.

I've been poking at this a bit in Cyberpunk 2077. I don't have comparable data right now for other GPUs, but DLSS Transformers definitely looks better. That will, as always, vary by the game and scene you're looking at, but let me see if I can drop some images to illustrate.

4K, DLSS Quality Transformers, FrameGen 2X (basically what we had with 40-series but using a new model):


4K, DLSS Quality Transformers, MFG 3X:


4K, DLSS Quality Transformers, MFG 4X:


The key thing from those three images is the FPS. Note also that the frametimes chart is fubar because RTSS / CapFrameX doesn't know how to deal with the new MFG pacing algorithm (yet). So in this case, MFG is providing nearly perfect scaling between 2X and 4X — 106 vs 212 FPS. Which means the input is still at the same rate (53 FPS) but you're getting more frames. There's a bit of wiggle room on the 3X result, just because this isn't a full benchmark. But I do have full benchmarks! For only the 5090...

CP77 FullRT 4K Native             AVG:  29.78   1%Low:  24.2
CP77 FullRT 4K DLAA               AVG:  30.38   1%Low:  23.9
CP77 FullRT 4K DLSSQ-CNN          AVG:  61.82   1%Low:  45.4
CP77 FullRT 4K DLSSQ-Transformers AVG:  58.15   1%Low:  42.8
CP77 FullRT 4K DLSSQT+FG2X        AVG: 106.88   1%Low:  73.7
CP77 FullRT 4K DLSSQT+FG3X        AVG: 153.75   1%Low:  93.7
CP77 FullRT 4K DLSSQT+FG4X        AVG: 195.67   1%Low: 104.1

So, interesting that DLAA actually outperformed native, probably because native doesn't use ray reconstruction and the denoisers for standard CP77 rendering are more complex than RR. The performance hit from transformers vs CNN looks to be relatively minor, about 6% (at least on the 5090).

Framegen gave an 83% boost to FPS with 2X mode, 164% with 3X mode, and 236% with 4X mode. Input framerate is 58.2 FPS without framegen, 53.4 FPS with 2X mode, 51.3 FPS with 3X mode, and 48.9 FPS at 4K mode. I dare say if that holds, people won't notice the minor change in input sampling rate and higher MFG levels will look smoother.

But that's really the crux of the story: What happens if you're not getting 50+ FPS on the input rate with framegen? Or more like what happens when the input sampling is only 25 FPS? In most games that I've tried with framegen (DLSS3 or FSR3), if you're getting a generated framerate of 50 FPS, the game feels very laggy. So I'd expect a similar situation with MFG running at 4X mode and 100 FPS.