Wednesday, May 6th 2026

NVIDIA GeForce 10-series "Pascal" Generation Turns 10

NVIDIA GeForce GTX 10-series graphics cards turn 10 today. In May 2016, NVIDIA debuted the GeForce GTX 1080, powered by the "Pascal" graphics architecture on the TSMC 16 nm FinFET foundry node. This would go on to be the final generation of NVIDIA GeForce GPUs to truly comply with Moore's Law. To illustrate, the GeForce GTX 1080, a predecessor to the current RTX 5080, needed a single 150-Watt 8-pin power connector, and could play AAA games of its time at 4K Ultra HD with the game being rendered at native resolution (no upscaling). "Pascal" established phenomenal standards of performance-per-Watt over the GTX 9-series "Maxwell" generation.
Add your own comment

124 Comments on NVIDIA GeForce 10-series "Pascal" Generation Turns 10

#26
Rulumi
ghaziReally drives home the stagnation in the industry... Entry level GPUs sold today are barely any more capable than a 1080 Ti and even have less VRAM...

10 years after the GeForce 256 came out, there were already DX10 only games that couldn't even initialize on a 3 year old GPU. The 3 year old GPU played games that couldn't initialize on a 5 year old GPU which played games that couldn't initialize on a GeForce 256. The GeForce 256 had 4 fixed function pixel pipelines and 10 years later the HD 5870 had 1600 programmable shaders.

What have we got now?
While there has been a big stagnation, I feel like in part that is also because the PS5 being limited to RDNA 1 instruction set (with RT), so a lot of developers aren't going to take the time to redo or utilize things the base PS5 couldn't even run properly or at all because actual hardware limitations. Already having to work with, target and port to different APIs for multiplatform games is probably already some work in itself to developers even if similar hardware nowdays.
Posted on Reply
#27
AusWolf
RulumiWhile there has been a big stagnation, I feel like in part that is also because the PS5 being limited to RDNA 1 instruction set (with RT), so a lot of developers aren't going to take the time to redo or utilize things the base PS5 couldn't even run properly or at all because actual hardware limitations. Already having to work with, target and port to different APIs for multiplatform games is probably already some work in itself to developers even if similar hardware nowdays.
That's not how it works. Before developers use some technology, that technology has to exist first. The same way no game had RT in it when Nvidia introduced it with Turing. RT first had to be available before game devs had a chance to use it. Game devs these days aren't utilising things because there are no things to utilise.
Posted on Reply
#28
JustBenching
cinemawareA lot of rose-tinted thinking in this thread :)

It'd be very interesting to know whether (and if, to what extent) Nvidia really became so evil and greedy they ran the GPUs to the current standtstill, or whether it's actually because reasons (like, real reasons) or maybe something in between. Unfortunately, the former narrative is so embedded in most people's minds we will probably never know. And objective investigations are a thing of the past in the era in which it's outrage that drives the views/clicks/likes.
Oh nvidia was insanely greedy according to the forum dwellers back then as well. Back then amd was preparing vega to give nvidia a smackdown.
AusWolfThe only reason we see any improvement these days is because the chips are bigger and they eat more power.
And nothing was different back then. The 1080ti was twice the transistor count of the 980ti, which is why it was faster.
Posted on Reply
#29
Rulumi
AusWolfThat's not how it works. Before developers use some technology, that technology has to exist first. The same way no game had RT in it when Nvidia introduced it with Turing. RT first had to be available before game devs had a chance to use it. Game devs these days aren't utilising things because there are no things to utilise.
Thst's the point? The PS5 being RDNA 1 based lacks things like Sampler Feedback, VRS, Mesh Shaders and others. NVIDIA has support for these newer instructions since Turing, AMD since RDNA 2, Intel Arc's Alchemist also support the newer instructions, Xbox Series S and Series X are also actually RDNA 2 so they have support as well, the Switch 2 GPU being Ampere derived also has support.

The PS5 is the only "modern" mainstream current gaming oriented one stuck with the older instructions (but for better or worse it may also be the more popular one of them within general users).
Posted on Reply
#30
Visible Noise
Legendary GPU.

There will be a lot of celebrated Nvidia GPU’s coming up. AMD, not so much 🫣
Posted on Reply
#31
AusWolf
JustBenchingAnd nothing was different back then. The 1080ti was twice the transistor count of the 980ti, which is why it was faster.
You didn't get my point. The 980 Ti and 1080 Ti were both 250 W cards.
RulumiThst's the point? The PS5 being RDNA 1 based lacks things like Sampler Feedback, VRS, Mesh Shaders and others. NVIDIA has support for these newer instructions since Turing, AMD since RDNA 2, Intel Arc's Alchemist also support the newer instructions, Xbox Series S and Series X are also actually RDNA 2 so they have support as well, the Switch 2 GPU being Ampere derived also has support.

The PS5 is the only "modern" mainstream current gaming oriented one stuck with the older instructions (but for better or worse it may also be the more popular one of them within general users).
Exactly. So what's preventing game devs from using such tech on machines that support it?

I can hardly recall a generation when current consoles were based on cutting edge tech.
Posted on Reply
#32
JustBenching
AusWolfYou didn't get my point. The 980 Ti and 1080 Ti were both 250 W cards.
Sure but is that really a good thing? If the 1080ti was a 300w card it would be even faster. People don't really care about power - even when nvidia was slashing power draw to half (some ada models did that) people did not give a damn. Look at the reviews of the 4060 and 4060ti.
Posted on Reply
#33
AusWolf
JustBenchingSure but is that really a good thing? If the 1080ti was a 300w card it would be even faster. People don't really care about power - even when nvidia was slashing power draw to half (some ada models did that) people did not give a damn. Look at the reviews of the 4060 and 4060ti.
Yes, more performance at the same power draw (and same PSU and cooling requirement as a result) is a good thing. It blows my mind that this is even a question for some people.

People didn't give a damn about the 4060 (Ti) because it's a weak card, barely even an upgrade over the 3060 which came with +4 GB VRAM as well.
Posted on Reply
#34
JustBenching
AusWolfYes, more performance at the same power draw (and same PSU and cooling requirement as a result) is a good thing. It blows my mind that this is even a question for some people.

People didn't give a damn about the 4060 (Ti) because it's a weak card, barely even an upgrade over the 3060 which came with +4 GB VRAM as well.
Hasn't that been always the case? New gpus offer more performance at the same power than previous gens. Legitimately I can't remember a generation that it wasn't the case. The 5090 is still ~25% faster locked to 400w than the 4090 is at 500w.

My point was that the 1080ti being a 250w card wasn't anything special. If it was a 300w card it would be even faster etc.
Posted on Reply
#35
AusWolf
JustBenchingHasn't that been always the case? New gpus offer more performance at the same power than previous gens. Legitimately I can't remember a generation that it wasn't the case. The 5090 is still ~25% faster locked to 400w than the 4090 is at 500w.
Manually locking power draw to be just slightly more efficient than last gen is not the same as offering a ton more performance at the same power draw out of the box.
JustBenchingMy point was that the 1080ti being a 250w card wasn't anything special. If it was a 300w card it would be even faster etc.
Probably not by much. GPUs used to come at the ideal point on their efficiency curve. Now they come at the peak to hide the fact that they barely have anything to offer on top of last gen. This was my point.
Posted on Reply
#36
CornyOC
My good old buddy 1080ti still runs strong in my mom's PC. Such a reliable and lovely card that serves you over a decade, and stays in the family! Once it will stop running or we will stop using it, it will 100% get a frame on the wall with a plaque.
Posted on Reply
#37
dtoxic
The biggest mistake Nvidia made the 10xx series,they made a quality product, that mistake wont be made again ever.
Posted on Reply
#38
Warigator
If performance and memory increases at constant price haven't been that poor since March 2017, then 2160p would be much more affordable and played in higher framerates today. Unfortunately, it hasn't been the case (if you don't count DLSS, FSR and XeSS). 1080p was way way more affordable and played in higher framerates in 2016 than in 2006. In 2006 you would need two GeForce 7800 GTX cards in SLI. In 2016 all you needed was one GTX 1070 and you were set for every 1080p game.
RulumiThst's the point? The PS5 being RDNA 1 based lacks things like Sampler Feedback, VRS, Mesh Shaders and others. NVIDIA has support for these newer instructions since Turing, AMD since RDNA 2, Intel Arc's Alchemist also support the newer instructions, Xbox Series S and Series X are also actually RDNA 2 so they have support as well, the Switch 2 GPU being Ampere derived also has support.

The PS5 is the only "modern" mainstream current gaming oriented one stuck with the older instructions (but for better or worse it may also be the more popular one of them within general users).
Doesn't PS5 have RDNA2? At least that's what I heard and read on www. Maybe RDNA 1.5? Certainly not exactly the same RDNA that's in 5700 XT. PS5 GPU is more like desktop PC's 6600 XT.
Posted on Reply
#39
MufasaV
cinemawareA lot of rose-tinted thinking in this thread :)

It'd be very interesting to know whether (and if, to what extent) Nvidia really became so evil and greedy they ran the GPUs to the current standtstill, or whether it's actually because reasons (like, real reasons) or maybe something in between. Unfortunately, the former narrative is so embedded in most people's minds we will probably never know. And objective investigations are a thing of the past in the era in which it's outrage that drives the views/clicks/likes.
After all, people still won't confront the fact that GTX 1080 and rtx 4080/5080 are roughly the same die size. But 4080/5080 are considered shrinkflation due to their die size, its part of what forms the "evil reputation". Especially HUB in his multiple videos who started the convo
Posted on Reply
#40
Krit
JustBenchingMy point was that the 1080ti being a 250w card wasn't anything special.
If there is something not special then that's RTX 5090 massive power draw performance gain only +35% @4k over RTX 4090 and +130w power draw.
GTX 1080Ti was 85% faster than GTX 980Ti @4k, +20w power draw and still it's at least 2.5x less expensive than RTX 5090 when even including inflation. 250w and 575w that's a massive difference noise and heat wise. Also GTX 1080 Ti price stayed almost the same over GTX 980 Ti where's RTX 5090 price significantly increased over RTX 4090. From every angle RTX 5090 looks like a shit.
JustBenchingPeople don't really care about power
Not true you can't say that for all. High power consumption will lead to noisy operation and heat.
Posted on Reply
#41
JustBenching
KritIf there is something not special then that's RTX 5090 massive power draw performance gain only +35% @4k over RTX 4090 and +130w power draw.
GTX 1080Ti was 85% faster than GTX 980Ti @4k, +20w power draw and still it's at least 2.5x less expensive than RTX 5090 when even including inflation. 250w and 575w that's a massive difference noise and heat wise. Also GTX 1080 Ti price stayed almost the same over GTX 980 Ti where's RTX 5090 price significantly increased over RTX 4090. From every angle RTX 5090 looks like a shit.
So surely, with these measly gains from the 4090 to the 5090, there must be a lot of competitors that have far surpassed the 5090 in performance. Right?

Physics have a wall. At some point, we hit that wall and performance stopped scaling. Do you think they can offer twice the performance of the 4090 at half the power but they decided not to for "reasons"? Like what are we even talking about here.
KritNot true you can't say that for all. High power consumption will lead to noisy operation and heat.
Then why are you buying xx70 tier cards that draw over 300 watts? The 1070 was sitting at 140 watts, your 9070xt draws over 300...you voted with your wallet that you don't care about power draw, didnt' you?
Posted on Reply
#42
Krit
JustBenchingThen why are you buying xx70 tier cards that draw over 300 watts? The 1070 was sitting at 140 watts, your 9070xt draws over 300...you voted with your wallet that you don't care about power draw, didnt' you?
300watts is not 600watts massive difference! I still run mine @273w @340w stock performance level.

GTX 670, GTX 970 and GTX 1070 where great gpus silent even out of the box no heat in to a pc case!
Posted on Reply
#43
JustBenching
Krit300watts is not 600watts massive difference! I still run mine @273w @340w stock performance level.

GTX 670, GTX 970 and GTX 1070 where great gpus silent even out of the box no heat in to a pc case!
300 watts is over twice of the pascal xx70 chips you are praising here. So clearly you don't seem to care about power since you bought a card with twice the power draw, right?

You can undervolt and tune the 5090 as well, moot point.
Posted on Reply
#44
Rexter
You can still play modern games with Pascal GPUs, which is absurd when you think about it. Imagine playing modern games in 2016 with a GPU from 2006. I know you cant imagine it because it wasnt possible.
Posted on Reply
#45
Krit
JustBenchingYou can undervolt and tune the 5090 as well, moot point.
Yes you can undervolt RTX 5090 but it will never be no the RTX 5070 Ti or RX 9070 XT level noise/heat wise. I'm talking about AIR cooling closed pc case. If fans will not spin faster RTX 5090 will be toasted and whole pc will be on higher temps. You pay a lot to get what worse noise levels!
JustBenching300 watts is over twice of the pascal xx70 chips you are praising here. So clearly you don't seem to care about power since you bought a card with twice the power draw, right?
Not happy about that at all but i can manage my RX 9070 XT @273watts to run at constant @30dBA which is quiet enough under load.
Posted on Reply
#46
Warigator
MufasaVAfter all, people still won't confront the fact that GTX 1080 and rtx 4080/5080 are roughly the same die size. But 4080/5080 are considered shrinkflation due to their die size, its part of what forms the "evil reputation". Especially HUB in his multiple videos who started the convo
GTX 1080 314 mm² for 599 USD vs RTX 4080 379 mm² for 1199 USD
double the MSRP and 20% larger die
so you pay 100% more for 20% larger gpu and 100% more VRAM
no one would complain if 4080 costed 600 USD and had TDP 180 W back in 2022, but it was not the case unfortunately, that's why people are rightfully disheartened
Posted on Reply
#47
lexluthermiester
AusWolfSure, Pascal is the GOAT of all Nvidia generations, but why is this news? Pascal isn't even supported by current drivers anymore.
The 10 year anniversary of release not a good enough reason? Seems like a good reason to me..
Posted on Reply
#48
Warigator
Base PS5 has a custom RDNA 2-based GPU, but not a full desktop/Xbox-style RDNA 2 implementation in terms of features like Variable Rate Shading, Mesh Shaders and Sampler Feedback. Calling it RDNA 1 is certainly going too far. Calling it custom RDNA 2-based, but not feature-complete in the same PC/Xbox/DX12U sense is much closer to the truth.

Also, I would not call VRS, Mesh Shaders and Sampler Feedback “newer instructions”. They are API/hardware features, not just GPU instructions. The distinction matters, because console GPUs have always been custom designs, and Sony does not expose the hardware through DirectX in the same way as Xbox or PC.

One of the reasons I originally fell in love with PC gaming and PC hardware was the feeling of rapid, visible progress. Every few years, GPUs were not just faster, but qualitatively different. New APIs, new shader models, new rendering techniques, large jumps in complexity and image quality, games that genuinely could not run on older hardware. It felt like the whole medium was moving forward very quickly.

Today, progress obviously still exists, but it feels much more incremental. A lot of the improvement is "hidden" behind techniques like upscaling, frame generation, or ray tracing with denoising. These things also matter, but they do not always create the same feeling of a clear generational leap in actual games. I don't care that much about reflections unless a game world is built from the ground up with them in mind. This also ties into a broader issue for me : modern hardware progress often feels less transformative than it used to.

I can see this even on my own PC. I currently use a Zen 5 CPU and an RDNA 4 GPU, so this is basically as current as consumer PC hardware gets right now. And yet many of the newer capabilities of this hardware are still not fully utilized in actual games. Very often, it feels like the hardware is ahead (mid-range and high-end), while the software and game engines take years to properly catch up. 52 core Intel 400DX is coming in Q4 this year and games still typically use only 3-7 cores. UE6 will change that.

1996 - 2006 : about 1000x faster and 192x more VRAM ($299 Voodoo Graphics vs $599 8800 GTX)
2006 - 2016 : 22x faster and 16x more VRAM ($599 8800 GTX vs $1199 Titan X Pascal)
2016 - 2026 : 8x faster and 2.67x more VRAM ($1199 Titan X Pascal vs $3999 RTX 5090)
(。﹏。*)
Posted on Reply
#49
A Computer Guy
TomgangAh Pascal. Fond memories. It gave us the GOAT GTX 1080 TI and the first hign-end card i got after moving away from SLI for the first time. Had a EVGA GTX 1080 TI FTW 3 in my back then X58 system. Good times in deed.

This was my system back then i had the GOAT GPU. Yes i had a GTX 1080 Ti pair with a I7 980X on X58. It was a great system, but time is a bitch and in the end the cpu could just not keep up with games. But i ran gtx 1080 TI in my X58 machine from 2017 to 2021, where i build my current AM4 based dual system.

That looks to be an Antec 1200 case.
Posted on Reply
#50
Tomgang
A Computer GuyThat looks to be an Antec 1200 case.
That is correct. Antec twelve hundred case.
Posted on Reply
Add your own comment
Nov 17th, 2026 17:48 CST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts