• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Unannounced Nvidia RTX 50 Super GPUs appear in Seasonic PSU calculator — unreleased graphics cards shown with 10-17% higher TGP over original models

MrGuvernment

Fully [H]
2FA
Joined
Aug 3, 2004
Messages
24,115
Will it happen?

Unannounced Nvidia RTX 50 Super GPUs appear in Seasonic PSU calculator — unreleased graphics cards shown with 10-17% higher TGP over original models​


https://www.tomshardware.com/pc-com...10-17-percent-higher-tgp-over-original-models

The GeForce RTX 50-series desktop graphics lineup has remained unchanged for just over a year now (since the introduction of the RTX 5050), and none of the conversations we've had at major trade shows suggests that a mid-cycle Super refresh will occur any time soon. But there are still signs that such an update could still happen at some point, and the latest sign comes from Seasonic, which has listed an RTX 5080 Super, an RTX 5070 Ti Super, and RTX 5070 Ti Super in its PSU wattage calculator.

You can click through the calculator and assemble a hypothetical system with these unannounced products inside.

To be useful, this calculator also provides board power numbers for these as-yet-unreleased cards, and that gives us another bit of juicy info. Given that no official specifications for these GPUs exist, it's impossible to say whether these figures are accurate. But it does allow us to speculate a bit on how they might stack up to existing products.

Unannounced RTX 50 Super-series TGPs
Graphics CardTotal Graphics Power (W)% Change
RTX 5070250--
RTX 5070 Super275*10%
RTX 5070 Ti300--
RTX 5070 Ti Super350*17%
RTX 5080380--
RTX 5080 Super415*15%
*As listed in Seasonic PSU calculator. Unconfirmed by Nvidia.

Seasonic gives this purported RTX 5080 Super a board power of 415W in its calculator, or 15% higher than the existing RTX 5080's 360W envelope. That makes sense, because the RTX 5080's GB203 GPU is already fully enabled, so any Super version of that card would have to lean on higher power limits and more aggressive clock speeds to see any baseline performance benefit.


That figure could also partially account for slightly higher power usage from 8 GB more GDDR7 memory on such a card. Past RTX 50 Super-series rumors have suggested that Nvidia will boost VRAM capacity on those products by moving to higher-density GDDR7 modules with 3GB of capacity each. GDDR7's power consumption as part of the overall board picture is relatively small, but more of it will still matter.

If Seasonic's figures are accurate, we should also expect a similarly sized TGP increase out of the RTX 5070 Ti Super, whose 350W rating is 17% higher than that of the RTX 5070 Ti. The RTX 5070 Super, meanwhile, gets only a 10% TGP bump over the RTX 5070, from 250W to 275W. Both of these cards rely on GPUs that are slightly cut down from their full available resources, so it's possible that Nvidia could boost their performance through a balance of enabling more Streaming Multiprocessors (SMs) in addition to boosting clocks through higher power envelopes.

Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Contact me with news and offers from other Future brandsReceive email from us on behalf of our trusted partners or sponsorsBy submitting your information you agree to the Terms & Conditions and Privacy Policy and are aged 16 or over.
Beware of extrapolating performance improvements directly from these percentages, though. Our own testing has shown that any real-world performance benefits from these power limit increases are likely to be smaller than those figures would suggest.

As our review of the MSI RTX 5090 Lightning Z showed, the largest performance boosts from higher power limits are likely to be concentrated in ray-traced and path-traced games, whose computational intensity is significantly higher than pure raster titles and is more likely to run the GPU into its power limits.

In any event, we shouldn't expect to see these products any time soon. Nvidia has instead been focused on getting more out of existing Blackwell silicon with software improvements such as DLSS 4.5 upscaling and Multi-Frame Generation multipliers up to 6X.

These technologies enable higher output frame rates and image quality with lower input resolution than past DLSS technologies, and the boost to both performance and image quality from those technologies in tandem has certainly made existing Blackwell products more appealing than they were at launch.

But as monitor refresh rates continue to climb thanks to ongoing improvements to OLED and LCD panels, and next-generation HDMI 2.2 connectors looming over 2027, a hardware update of some kind that boosts baseline performance and potentially implements support for those standards seems practical at some point. Given these primarily consumer-focused improvements, an announcement at CES 2027 or Computex 2027 might make sense. As with any future product rumors, however, only time will truly tell.
 
I can’t wait to see what this costs.
Can totally see $1500 for 5080s, $1100 for 5070tiS, and $850 for 5070S. Pretty large power increases signal that extra overclock which were intentionally handicapped in the initial specs, and 50% more RAM can easily justify a min $2-300 increase in this crappy timeline.
 
3 GB gddr7 chips could be quite expensive if that what they use (and could explain the absence of a 5060 12GB which would have been an interesting one for the super series)
 
If there ever was a tone deaf, "who gives a fuck" moment to launch a shitty refresh... yeah it's now.
Pretty much, as they will definitely be even more so cost prohibative than the current cards, because no way they'll keep current MSRPs for the Supers.

I hope the 5090 Super is 5k MSRP though if it happens. That way current 5090 owners will still have to pay 2k+ even after selling their current cards. Which enables most of them to upgrade (que 5090 owner saying they'll buy it regardless), because even worse than that are the people buying their used cards for 2-3k. Dunno why they settle for the 5090 either when a true [H] enthusiest would have the RTX Pro 6000 with triple the VRAM and extra cores. 😜
 
I hope the 5090 Super is 5k MSRP though if it happens.
i doubt will see a 5090 super, Seasonic could just be speculating here and that why they did not added one, but like for the 4090 there is very little reason for Nvidia to do a 5090 super.
 
Can totally see $1500 for 5080s, $1100 for 5070tiS, and $850 for 5070S. Pretty large power increases signal that extra overclock which were intentionally handicapped in the initial specs, and 50% more RAM can easily justify a min $2-300 increase in this crappy timeline.

RTX5080 is notoriously good at overclocking, so I have no doubt Nvidia left a bit on the table. In terms of the price, there's MSRP, and then there's what it's actually going to sell for retail. It's going to be interesting!
 
RTX5080 is notoriously good at overclocking, so I have no doubt Nvidia left a bit on the table. In terms of the price, there's MSRP, and then there's what it's actually going to sell for retail. It's going to be interesting!
As much as I hack on Intel, NVIDIA, and AMD's prices on their graphics cards, I agree that I'm impressed by the overclockability of some of the RTX 5000 series cards (I only got to test the 5070 and 5070 Ti). One RTX 5070 I tested got up to +400 Core Clock in MSI Afterburner at stock voltage, peaking at 3360MHz. One RTX 5070 Ti I tested got up to +500 Core Clock in MSI Afterburner at stock voltage, peaking at 3307MHz, but the weird part is that it only got up to 261.4W's. Other RTX 5070 Ti's can get up to 339W's.

While there's room to improve with more wattage, it may not always mean more performance (like the RTX 3070 and RTX 3070 Ti). It'll at least be interesting if they do release the Supers for the 5000 series.
 
My 4070S has been such a great card at 1440p, I'd have no problem paying for a 5070S...
 
Pretty much, as they will definitely be even more so cost prohibative than the current cards, because no way they'll keep current MSRPs for the Supers.

I hope the 5090 Super is 5k MSRP though if it happens. That way current 5090 owners will still have to pay 2k+ even after selling their current cards. Which enables most of them to upgrade (que 5090 owner saying they'll buy it regardless), because even worse than that are the people buying their used cards for 2-3k. Dunno why they settle for the 5090 either when a true [H] enthusiest would have the RTX Pro 6000 with triple the VRAM and extra cores. 😜

I don't really see them making a 5090 Super. The problem is that if they increase the VRAM capacity... well the 5090 can already run some LLM models pretty decently. Increase it by just a smidgen and it's suddenly competing with many of their higher priced "pro" offerings. They'd have to jack up the price quite a bit.

Keep the VRAM the same but increase the compute, and it's faster than their 6000 PRO. If anyone finds a way to use heterogeneous VRAM mixtures (ie NVIDIA processor using some cheaper intel chips for higher context), suddenly your 6000 demand may plummet.
 
As much as I hack on Intel, NVIDIA, and AMD's prices on their graphics cards, I agree that I'm impressed by the overclockability of some of the RTX 5000 series cards (I only got to test the 5070 and 5070 Ti). One RTX 5070 I tested got up to +400 Core Clock in MSI Afterburner at stock voltage, peaking at 3360MHz. One RTX 5070 Ti I tested got up to +500 Core Clock in MSI Afterburner at stock voltage, peaking at 3307MHz, but the weird part is that it only got up to 261.4W's. Other RTX 5070 Ti's can get up to 339W's.

While there's room to improve with more wattage, it may not always mean more performance (like the RTX 3070 and RTX 3070 Ti). It'll at least be interesting if they do release the Supers for the 5000 series.
Totally agree - with all things there’s a point of diminishing returns, and it seems like Nvidia realized this pretty early on with the makeup of the Blackwell silicon that got delivered to them. The yield for viable silicon must have been better if they kept the voltage/wattage down and slightly gimped overall performance, while only allowing the flagship to run to its theorieic limit. Basically they would be better off hitting performance per watt sweet spot on the non-flagship chips, and with the 5090 they knew people would only up just about any amount since they purposely sandboxed performance tiers via their contractual driver clock and power limitations.

The announcement of a rumored 5090 SE which is smaller wafer, lower power, but near 5090 performance even further bolsters this theory. Now they can further maximize profits by using the less than perfect 5090 chips on the SE while charging only slightly less, and dedicating the good silicon to the Pro series and its ~3x profit margin.

The more you buys, the more you save indeed.
 
The announcement of a rumored 5090 SE which is smaller wafer, lower power, but near 5090 performance even further bolsters this theory. Now they can further maximize profits by using the less than perfect 5090 chips on the SE while charging only slightly less, and dedicating the good silicon to the Pro series and its ~3x profit margin.
not sure about near 5090 performance with so much cores disabled (it is not smaller, same die), it would be the gaming version of the :
https://www.techpowerup.com/gpu-specs/rtx-pro-5000-blackwell.c4276

which according to TPU estimate would be about a 4090.
The 5090 are far from perfect they use 21,760 of the 24,576 cores, the best chips goes usually to the RTX pro 6000 that use 24,064 enabled cores.
 
Just looking at the paper specs, the 5090 SE cuts off a lot of cores, not just a little. That doesn't directly scale into performance, so it could still be close, but I am very, very skeptical. It's about 33% weaker, or putting it another way the 5090 has about 1.5x more cores.
 
not sure about near 5090 performance with so much cores disabled (it is not smaller, same die), it would be the gaming version of the :
https://www.techpowerup.com/gpu-specs/rtx-pro-5000-blackwell.c4276

which according to TPU estimate would be about a 4090.
The 5090 are far from perfect they use 21,760 of the 24,576 cores, the best chips goes usually to the RTX pro 6000 that use 24,064 enabled cores.
Yeah sorry misread some of the post language, does seem like the “cut down” actually means disabling not physical removal.

Good call on the current Blackwell pro 5000 basically being the same GPU. So Nvidia keeping the 30% or so gap between the flagship and the lower spec, while adding another tier at a price premium above the 5080
Just looking at the paper specs, the 5090 SE cuts off a lot of cores, not just a little. That doesn't directly scale into performance, so it could still be close, but I am very, very skeptical. It's about 33% weaker, or putting it another way the 5090 has about 1.5x more cores.
Yeah that amounts to roughly 15% more performant than the 5080, so maybe should be named the 5080ti even if it uses the same base chip as the 5090. Ends up taking a hit out of 4090 current pricing, though that could be Nvidias strategy: instead of having the original owners see a profit from selling them at ~$2k why not release a model that can be sold near that price/performance level and take the profit themselves.
 
Back
Top