Why you can trust Tom's Hardware
What's there to say about a $2,000 graphics card? Yes, it's fast — usually. Yes, it can use a lot of power — sometimes. When it does, the Founders Edition can get quite hot, uncomfortably so. It's also really expensive, and depending on supply and demand, retail pricing could go even higher. (Spoiler post-launch: It has, with most cards on eBay now hitting more than double the MSRP.)
The RTX 5090 nominally 'only' costs $400 more than it's 4090 predecessor, a 25% price increase. It's also about 25% faster (at 4K) in our testing, though these are very much preliminary results. But supply looks to be very tight, which means prices are going much higher than $1,999. Some of the AIB partner cards even cost over 50% more than the base MSRP.
The RTX 5090 is a bit of a messy situation — a work in progress. Certain games and apps need updates and/or driver work. Thermal and fan management may also need some tweaks. Nvidia usually does pretty good with drivers, but new architectures can change requirements in somewhat unexpected ways, and Nvidia needs to continue to work on tuning and optimizing its drivers. We're also sure Nvidia doesn't need us to tell it that.
Gaming performance is very much about running 4K and maxed out settings. If you only have a 1440p or 1080p display, you're better off saving your pennies and upgrading you monitor — and probably the rest of your PC as well! — before spending a couple grand on a gaming GPU. Unless you're also interested in non-gaming applications and tasks, particularly AI workloads. If that's what you're after, the RTX 5090 could be a perfect fit.
The RTX 5090 is the sort of GPU that every gamer would love to have, but few can actually afford. If we're right and the AI industry starts picking up 5090 cards, prices could end up being even higher. Even if you have the spare change and can find one in stock, it still feels like drivers and software could use a bit more time baking before they're fully ready.
Due to time constraints, we couldn't fully test everything the RTX 5090 has to offer. However, we did spend a fair amount of time poking around at Cyberpunk 2077, running in full RT mode with various levels of Multi Frame Generation (MFG). The results aren't nearly as clear-cut as Nvidia would like to pretend. With MFG4X and full path tracing, the 5090 can more than double the performance of the 4090... but still end up only feeling slightly faster. Input latency and sampling rates still matter, in other words.
That doesn't mean MFG is inherently bad, but it's also not universally good. If the best you can do with a particular game is around 30 FPS without MFG, getting over 100 FPS with MFG does look and feel better, subjectively. It doesn't feel three times as fast, just like DLSS 3 framegen didn't make games feel up to twice as fast. But it's not a bad extra to have available.
One big problem with Blackwell RTX is the marketing. If Nvidia as an example takes MFG4X at 200 FPS and compares it to framegen at 100 FPS, both are actually rendering at 50 FPS and then generating extra frames. To pretend that MFG4X in such a scenario is "twice as fast" is ludicrous. It may look smoother, and subjectively it could even feel somewhat better (because visuals are linked to feel in fuzzy ways). But it absolutely doesn't feel twice as fast or twice as good. Carry it to the next level and if Nvidia could generate 99 frames between two rendered frames, it wouldn't be "100 times as fast." At some point the additional frames become completely meaningless if the input sampling rate remains steady.
But really, it's about the specs and performance of the 5090. It's doubtful that any GPU will beat it in the next two years, outside of a potential RTX 5090 Ti / 5090 Super / Titan Blackwell. It has more VRAM than any other consumer GPU is likely to have in the next two years as well, with 78% more memory bandwidth than the RTX 4090. It can do things that the 4090 simply can't — or at least, not as well.
There's also the DeepSeek news making the rounds has to make us wonder what else might change in the coming years. Nvidia isn't the only game in town, for AI or graphics, and some of the new features in Blackwell may end up proving less critical than a clever software algorithm. If DeepSeek managed this with sanctioned GPUs plus a stockpile of older and/or slower Nvidia chips, what might it manage with RTX 5090D? And how far will the U.S. go to try and keep Blackwell GPUs out of China? We'll find out in the coming months and years.
And there's more to come. We should be getting in a few AIB partner 5090 cards in the coming days, and it will be interesting to see how those stack up against the 5090 Founders Edition. I'll admit to being skeptical of the cooling abilities of the 5090 FE when it was first revealed, and in some cases it gets quite a bit warmer than the 4090 FE. Worst-case, it can match the scorcher RTX 3080 Ti FE for surface temperatures of 75C or more. It's a smart looking design that makes massive 3-slot and 4-slot variants look like weaker engineering... but I have little doubt it's going to run hotter than the larger AIB cards.
For those that can't afford or justify spending two grand, we also have the RTX 5080 coming next week. Thankfully, a lot of the testing overlaps with what we've already done for this article. Stay tuned to see how it stacks up, and if MFG works just as well on a $999 card as on a $1,999 GPU.
Ultimately, as the fastest GPU we're likely to see for the next two years, with improved AI capabilities and extras like DLSS 4 Multi Frame Generation, the RTX 5090 delivers a great next-gen GPU experience. It's not twice as fast as a 4090, or even 50% faster in most cases, but the days of huge generational gains are fading in the rearview mirror. It is faster, and it's likely to improve further as Nvidia addresses the early driver pains. If you need or want the fastest graphics card around? The GeForce RTX 5090 is it. It's not a great value, at all, but that's never been the purpose of halo GPUs.
- MORE: Best Graphics Cards
- MORE: GPU Benchmarks and Hierarchy
- MORE: All Graphics Content
Current page: Nvidia RTX 5090: A work in progress
Prev Page Nvidia RTX 5090: Power, Clocks, Temps, and NoiseJarred Walton is a senior editor at Tom's Hardware focusing on everything GPU. He has been working as a tech journalist since 2004, writing for AnandTech, Maximum PC, and PC Gamer. From the first S3 Virge '3D decelerators' to today's GPUs, Jarred keeps up with all the latest graphics trends and is the one to ask about game performance.
-
Crazyy8 Quick look, raster performance seems a bit underwhelming. Weird that the RTX 5090 can be slower than the 4090(in niche cases). Wasn't going to buy the 5090 anyway, too expensive for a plebe like me. Looking forward to DLSS 4 and how amazing(or not)it'll be.Reply -
Gururu Amazing but expected as far as I am concerned. I don't think there is a lot of need to compare against anything including AMDs new cards. It was brilliant to pair with the 13900 with crazy interesting results. Will read a few more times to glean more details. (y)Reply -
Admin said:We also tested the RTX 5090 on our old 13900K test bed, with some at times interesting results. Some games still seem to run faster on Raptor Lake, though overall the 9800X3D delivers higher performance. The margins are of course quite small at 4K ultra.
For me, as a 13900K owner, that's a consolation :cool: -
Gaidax Okay, that IS a sick cooler that actually manages to do the job.Reply
I bet aftermarket 4 slot monstrocities will do better, but for 2 slots 600w that's insane. -
m3city Products like this should receive 3stars max. Great performance but at what cost? Is it the right direction that power draw increases at each iteration? Is it worth to chase max perf each time? For me it would be perfect if 5000 series stayed at same TDP as previous ones - meaning better design, better gpu - with understandably lower increase of perf compared to 4000. And then, 6000 series to have even reversed direction: higher perf with drop of TDP.Reply
And secondary, how come 500W gpu can be air cooled, but nerds on forums will claim you absolutely NEED water cooling for 125W ryzen, cause "highend"?. Yeah, i know 125W means more actual draw. -
redgarl Okay Jarred... you are shilling at this point.Reply
4.5 / 5 for a 2000$ GPU that barely get 27% more performances?
While consuming 100W more than a 4090?
And offering the same cost per frame value as a 4090 from 2 years ago?
Flagship or not, this is horrible.
Not to mention the worst uplift from an Nvidia GPU ever achieved... 27%...
https://i.ibb.co/4fks6Gt/reality.jpg -
redgarl Did you bench into an open bench or a PC case? I am asking because there is some major concerns of overheating because the CPU coolers is choked by the 575W of heat dissipation inside a closed PC Case. If you have an HSF for your CPU, then you are screwed.Reply
https://uploads.disquscdn.com/images/7a5bf4d586b20ffe0aa6281c57d419012a32cbdabd43b3e8050d2aa9a00d6cc1.png -
oofdragon 20% better at 4K and 15% better at 2K, all that having 30% more cores and etc............... got it. Oh boy the 5080 and 5070 are sure going to disappoint a lot of people.Reply
The good news is the RX 9070 will bring 4070 Ti Super performance to the table around $500 including the VRAM, ray tracing and dlss image quality. AMD will prolly counter the multi frame gen nonsense with something like the LSFG 3.0 is doing and smart buyers will finally have a good GPU to replace their 3080 or 6700 XT. -
vanadiel007 They should have given it code name sasquatch, because that's the chance you will be seeing these sell for $2,000 in the coming months.Reply
More like $3,000 and a lot of luck needed to find one in stock.
I pass on it. -
YSCCC a real space heater inside the case, and extremely expensive with not great raw performance increase... sounds like built for those with more money than brain or logic..Reply