Monday, October 4th 2021

NVIDIA Rumored To Launch RTX 3090 SUPER in January 2022

NVIDIA has been preparing a new flagship graphics card with their RTX 3090 SUPER featuring a fully unlocked GA102 GPU. The RTX 3090 SUPER will include 10,752 CUDA cores, 336 Tensor cores, and 84 RT cores paired with 24 GB of GDDR6X memory on a 384-bit wide memory bus. These speed improvements are set to increase the cards TDP to 400 W compared to 350 W for the base RTX 3090. We have recently seen a new rumor from @hongxing2020 that claims NVIDIA will be launching the RTX 3090 SUPER, a refreshed RTX 3070 Ti with 16 GB memory, and the RTX 2060 12 GB in January 2022. The RTX 3090 SUPER and RTX 2060 12 GB launches have been expected for some time but this is the first mention we have seen of an RTX 3070 TI 16 GB.
Source: @hongxing2020 (via VideoCardz)
Add your own comment

40 Comments on NVIDIA Rumored To Launch RTX 3090 SUPER in January 2022

#26
ThrashZone
FlankerAs long as the prices remain outrages, all GPU releases are just cool stories to me
Hi,
Yeah only cool if you have a bestbuy that sells them near by too lol
Otherwise you'll be on a road trip camp out.
Posted on Reply
#27
AusWolf
ThrashZoneHi,
Yeah only cool if you have a bestbuy that sells them near by too lol
Otherwise you'll be on a road trip camp out.
Or you can decide to be happy with what you have. There's lots of folks out there crying with 980s and 1070s whose only problem is not getting their two-yearly shiny new GPU fix that they actually don't need.
Posted on Reply
#28
wolf
Better Than Native
nguyenAll high end SKUs 3090 (Asus Strix, MSI SuprimX, Zotac Holo AMP, etc..) already use 420W+ at stock :roll:
And here I am (as are many others) undervolting for massive efficiency gains. I've gotten to around -9% of stock performance for -30% energy used, or ~stock performance at -~20% energy.
Posted on Reply
#30
nguyen
wolfAnd here I am (as are many others) undervolting for massive efficiency gains. I've gotten to around -9% of stock performance for -30% energy used, or ~stock performance at -~20% energy.
And capping FPS too and watch 3090 sip power like a mouse :D
Posted on Reply
#31
AusWolf
wolfAnd here I am (as are many others) undervolting for massive efficiency gains. I've gotten to around -9% of stock performance for -30% energy used, or ~stock performance at -~20% energy.
Fun facts with my RTX 2070:
A power target of 71% (125W TDP instead of 175) gives me around -7% performance compared to stock, which is barely noticeable even with an on-screen fps counter.
A power target of 114% (200W TDP instead of 175) gives me no observable or measurable performance gain, only more heat and noise.

This makes me question manufacturers' choice of TDP. Does our new PC gaming world really revolve around that extra 1% so much? :confused:
Posted on Reply
#32
londiste
AusWolfThis makes me question manufacturers' choice of TDP. Does our new PC gaming world really revolve around that extra 1% so much? :confused:
Yes :)
And much more so of the competitor has that 1%.
If you want a specific recent example, look at 6900XT "XTXH" cards. - extra 30% and 100W over 6900XT for 5-7% performance.

Clocking and targeting GPUs beyond the nice place on the efficiency curve has been AMD thing for a long while. With Turing and especially with Ampere, Nvidia followed suit.
As with your example lowering power target shows that quite clearly.

Undervolting today is a much more complex question. Generally undervolting guides for something like Ampere simply set the maximum voltage and frequency and are done with that. Actual undervolting seems to be a smaller part of the process.
Posted on Reply
#33
las
Xex360Why ? At least non-LHR you could make some money back, with LHR you still pay the same amount but for an inferior product.
Gamers will be gaming, not mining. At this point you will earn peanuts from GPU mining unless you have alot of GPUs that run 24/7 using custom firmware anyway.

You might as well buy upcoming coins and hope they explode instead of wasting electricity. That's what I did. Did not mine for one minute, yet earned alot of money from bitcoin, ethereum and dogecoin so far. However it's a gamble and there's many ways to make money.
Posted on Reply
#34
AusWolf
londisteYes :)
And much more so of the competitor has that 1%.
If you want a specific recent example, look at 6900XT "XTXH" cards. - extra 30% and 100W over 6900XT for 5-7% performance.
That's what I call a waste. Something's seriously wrong with the gaming industry from this perspective.
Posted on Reply
#35
wolf
Better Than Native
AusWolfThis makes me question manufacturers' choice of TDP. Does our new PC gaming world really revolve around that extra 1% so much?
Yeah It seems like a combination of things, going for those last few % to beat out a competitor or advertise larger gen-on-gen increases. Also, the frequency/voltage table would need to be suitable for 100% of cards that come off the production line, pushing them to use an even higher voltage per frequency in order to guarantee stability.

Overclocking used to be a lot of fun, getting 15..20...25%++ out of CPUs and GPU's in the past with little effort. Nowadays the vendor pushes them pretty much to the limit of their capability, where you're fairly lucky to get 10-12% extra under non-extreme conditions like LN2.

So I scratch my tweaking / overclocking / optimizing itch by undervolting, keeping the most performance I can (perhaps even a few % points more) while drastically reducing power draw and pumping up efficiency to fun heights.

I'd love to see a comparison of Pascal v Turing v Ampere, all stock vs all UV'd to get a glimpse of stock efficiency vs UV's efficiency gains gen-to-gen. Would be bloody hard to pull off though, silicone lottery and all.
Posted on Reply
#36
AusWolf
wolfYeah It seems like a combination of things, going for those last few % to beat out a competitor or advertise larger gen-on-gen increases. Also, the frequency/voltage table would need to be suitable for 100% of cards that come off the production line, pushing them to use an even higher voltage per frequency in order to guarantee stability.
Or they could drop a few MHz from the boost table to be able to decrease the voltage significantly, resulting in much lower power consumption at the cost of a few frames per second. But maybe it's just me - my e-peen doesn't grow in correlation with the extra 1% performance squeezed out of my hardware.
wolfOverclocking used to be a lot of fun, getting 15..20...25%++ out of CPUs and GPU's in the past with little effort. Nowadays the vendor pushes them pretty much to the limit of their capability, where you're fairly lucky to get 10-12% extra under non-extreme conditions like LN2.
This is the side of it that I'm actually happy about. Getting basically maximum performance right out of the box is brilliant. :) I love building PCs, but I also love it when they just work.
wolfI'd love to see a comparison of Pascal v Turing v Ampere, all stock vs all UV'd to get a glimpse of stock efficiency vs UV's efficiency gains gen-to-gen. Would be bloody hard to pull off though, silicone lottery and all.
I don't know about UV, but at stock, there's very little change imo - the 1080, 2070 and 3060 all perform similarly (if you don't count RT and DLSS), consuming about the same amount of power.
Posted on Reply
#37
nguyen
AusWolfOr they could drop a few MHz from the boost table to be able to decrease the voltage significantly, resulting in much lower power consumption at the cost of a few frames per second. But maybe it's just me - my e-peen doesn't grow in correlation with the extra 1% performance squeezed out of my hardware.
4K gaming just put higher load on the core, so the freq/voltage end up on the lower part of the Perf/Power curve.


For example, at 1440p with the stock power limit, my core clocks is at 2145mhz/1.0V, but @4K and stock power limit, the core end up at 1920mhz/850mV, at this V/F point the Perf still scale almost linearly with power and it's a waste not to give the core some more power to work with.
Posted on Reply
#38
AusWolf
nguyen4K gaming just put higher load on the core, so the freq/voltage end up on the lower part of the Perf/Power curve.


For example, at 1440p with the stock power limit, my core clocks is at 2145mhz/1.0V, but @4K and stock power limit, the core end up at 1920mhz/850mV, at this V/F point the Perf still scale almost linearly with power and it's a waste not to give the core some more power to work with.
Interesting. I wonder why that is.
Posted on Reply
#39
londiste
AusWolfInteresting. I wonder why that is.
An educated guess would be that the balance of the load on different units or subunits changes based on resolution (among other things) and something that is used more on 4K runs at higher power cost. The exact culprit is probably heavily load-dependent.
Posted on Reply
#40
saki630
Will i be able to pick up at 3080 for $650 like I did my 1080ti in 2018? It makes no difference what they release when there is nothing we can buy at reasonable prices.
Posted on Reply
Add your own comment
Nov 19th, 2026 05:16 PST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts