News RTX 5070 Ti manufacturing defect cuts performance by up to 10% — 88 ROPs vs 96 ROPs (design)

I knew when they had the major issues of Blackwell server ai cards that top end chips would likly get the shift ,the leftovers as there not as valuable as AI cards for buisness.

Now if someone beats nvidia in the gpu for gamer realm than maybe be better but when ur talking 10to15percent year over year I can't see why anyone would wanna upgrade I love nvidia always had nvidia cards but 10percent drop bought nullifies gen on gen performance I would think
 
I knew when they had the major issues of Blackwell server ai cards that top end chips would likly get the shift ,the leftovers as there not as valuable as AI cards for buisness.

Now if someone beats nvidia in the gpu for gamer realm than maybe be better but when ur talking 10to15percent year over year I can't see why anyone would wanna upgrade I love nvidia always had nvidia cards but 10percent drop bought nullifies gen on gen performance I would think
And for that %5 improvement over last gen you can fork over huge sums. 749 retail? You wont see that. Maybe in a few months, most likely never.

I have a 3060 so should see a substantial improvement considering i am jumping two whole tiers. Instead i get one tier in the 4000 series and half a tier with the 5000 series, it seems. So in essence a %15 or %20 improvement on my 3060 for jumping two whole tiers. Mad.

Not gonna do it. Not for that kind of money.
 
  • Like
Reactions: George³
Stuff like this are why I always try to avoid buying new products at launch. Of course, that's no guarantee, as it took more than a year for Raptor Lake's problems to surface.

You can also usually save a bit of money, if you wait - even leaving aside the matter of launch shortages. I get that not everyone has the luxury of being able to wait, but it's a good idea if you can.
 
I knew when they had the major issues of Blackwell server ai cards that top end chips would likly get the shift ,the leftovers as there not as valuable as AI cards for buisness.
No, the server Blackwells they launched last year use a very different design. They do not share the same silicon with any of the RTX 5000 cards.

There will be both workstation and server cards that do share dies with these gaming cards, but they have yet to launch. You can look at prior examples, like the RTX 6000 Ada and L40, which shared the same silicon die as the RTX 4090, for instance.

However, the Hopper H100 and H200 continued a long legacy of HPC/AI chips that had no equivalent client card. And now the Bx00 chips do the same. The last time that ever happened was the V100 that was incorporated into the Titan V, back in 2017. The newer 100-series dies do not even have the necessary graphics functional units needed to use them for gaming, which slams the door shut on that era.
 
749 retail? You wont see that. Maybe in a few months, most likely never.
PNY makes a RTX 5070 Ti with that MSRP. If I bought a RTX 5070 Ti, I might be tempted to go with that one, since PNY also made Nvidia's workstation and server cards, at least in the past - not sure if that's still true. Those cards had like 5 year warranties, which tells me PNY is not just any second-tier brand.
 
Last edited:
  • Like
Reactions: TCA_ChinChin
How little actual resources and care are they leaving for consumer graphics cards with this many failures?
If you haven't been following the saga of their HPC/AI Blackwells, it hasn't only been on client GPUs that Nvidia has been slipping up, lately.

Not to excuse Nvidia's failures, but I think it's worth considering that each new GPU generation is the fastest and most complex ever launched. So, they not only have to get right all of the challenges they mastered in the past, but also new challenges they didn't face before. On top of all that, they keep increasing power limits, which poses new challenges - and that's where a lot of their stumbles have been.

That said, we should expect and demand better from one of the world's most valuable companies. I'm just saying, as someone who works in tech, I try to keep a little humility and remember that perfection is always an ideal but rarely a reality.
 
So we could say this rtx5070ti discovery means they really selling a rtx5060ti or a vanilla, rtx5070, like fullboat. As if, nVdia did not know.

look at this as a cheap thrust to penetrate a hungry enthusiast market this moment, with little on the shelf.....
 
Every day seems like something new with Nvidia. I think using term "AI" every other sentence really got in the way of quality. Now we just wait to see what AMD is going to do because at some point, something has to work in the favor of the consumer with all these shenanigans.

Ooof.
 
5090's, 5080's, 5070Ti's missing ROPS, 5090's exploding, 12VHPWR cables setting on fire, PhysX 32-bit support gone... I didn't want to believe it at first, but this is quite literally the worst Nvidia launch ever. And even for people like me, who still want one of those cards, despite the defects, they can't buy them, coz there's no stock, or its massively upmarked and being scalped.
 
The RTX 5xxx series launch is starting to become a debacle.
That was my thought as well.

We had an unusual amount of build up and hype followed by an actual paper launch with no product to buy at all, anywhere. Ten people buying a 5090 in one whole country, after the official launch, is not a launch.

Then we had the fake frames debate, which are still fake frames, any which way they want to "frame" the argument.

Then we had a week or so of driver related issues with reports of BSOD and actual dead cards as a result of those BSOD.

Followed by melted connectors, version 2.0.

Did somebody not blow up a capacitor near the power connector yesterday and fry their card? Was that a 5000 series?
 
  • Like
Reactions: bit_user
PNY makes a RTX 4070 Ti with that MSRP. If I bought a RTX 4070 Ti, I might be tempted to go with that one, since PNY also made Nvidia's workstation and server cards, at least in the past - not sure if that's still true. Those cards had like 5 year warranties, which tells me PNY is not just any second-tier brand.
While buying a 4000 series card may be an attractive proposition at this point in time, considering the launch issues of the 5000 series, i cant see myself forking over huge sums for an obsolete and dead end card. I am not even sure i can find a 4070 ti without the price being jacked up to offensive levels.

If i am going to fork over lots of money for a GPU then i might as well stick with current tech and not a last gen card.

I get the idea of buying slightly older tech. I did it twice last year. I bought two AMD 5000 series CPU's in the span of one year for the same system.

Moving from a ryzen first gen 1500x to a R5 5500 was a huge jump. So was the jump to a R7 5800x. I paid 130 pounds for a CPU that people paid hundreds for not all that long ago. And the CPU is still more than capable and will continue to do so for a number of years.

I used the first gen ryzen for 7 years i think. While not being a 7 class it did me fine for a long time. AM4 users were really lucky to have that socket last that long. I mean here i am in 2025 buying new CPU's for a socket that is, what, eight years old?

And AMD is still releasing brand new SKU's in 2025 for the AM4 platform. They are not done yet.
 
This is unacceptable really.

Things like that should be basics, something they should have caught in automated validation without batting an eyelash.

The worst part is if such a basic and evident thing was missed, what else do they let slip through the cracks?
 
  • Like
Reactions: valthuer
I don't really think it's some grand conspiracy here, merely incompetence.

Which is still pretty bad for a trillion dollars' worth company.
This seems to me like cutting back on product testing and, cutting quality control, presumably to boost profits. If it is the case, it looks like the policy is backfiring.
 
That was my thought as well.

We had an unusual amount of build up and hype followed by an actual paper launch with no product to buy at all, anywhere. Ten people buying a 5090 in one whole country, after the official launch, is not a launch.

Then we had the fake frames debate, which are still fake frames, any which way they want to "frame" the argument.

Then we had a week or so of driver related issues with reports of BSOD and actual dead cards as a result of those BSOD.

Followed by melted connectors, version 2.0.

Did somebody not blow up a capacitor near the power connector yesterday and fry their card? Was that a 5000 series?
Don't forget this:

While buying a 4000 series card may be an attractive proposition at this point in time, considering the launch issues of the 5000 series, i cant see myself forking over huge sums for an obsolete and dead end card. I am not even sure i can find a 4070 ti without the price being jacked up to offensive levels.
Sorry, that was due to brain rot. My intention was to write 5070 Ti (posted updated).
 
This seems to me like cutting back on product testing and, cutting quality control, presumably to boost profits. If it is the case, it looks like the policy is backfiring.
A company like Nvidia has much more to lose from execution failures than the cost of a few extra workers' salaries. I see no plausible argument they were simply too cheap to hire enough staff.

I think the most likely scenario is that they're too focused on datacenter/AI and that's starving their client GPU business. It takes a long time for these companies to hire & train more staff, so the natural inclination is for them to pursue new or higher-priority projects by moving resources from lower-priority or legacy ones.

Also, don't forget the joint ventures they're doing with MediaTek, the first of which is their Digits box: