NVIDIA GeForce RTX 5050, RTX 5060, and RTX 5060 Ti Specifications Leak

[AleksandarK]

NVIDIA's upcoming GeForce RTX 50 series mainstream lineup has been leaked, thanks to the well-known leaker kopite7kimi, revealing the complete specification profile of the RTX 5050, RTX 5060, and RTX 5060 Ti graphics cards. The entry-level RTX 5050 features GB207-300-A1 silicon on a PG152-SKU50 board with 2,560 CUDA cores and 8 GB of the older GDDR6 memory across a 128-bit interface at 130 W, while the mid-tier RTX 5060 utilizes GB206-250-A1 silicon on a PG152-SKU25 board housing 3,840 CUDA cores with 8 GB of the latest GDDR7 memory at 150 W. The more powerful RTX 5060 Ti implements GB206-300-A1 silicon with two board versions, PG152-SKU10/15, presumably for two memory configurations. It features 4,608 CUDA cores paired with either 8 GB or 16 GB of GDDR7 memory and a 180 W power envelope.

Most notable is the adoption of next-generation GDDR7 memory technology in both RTX 5060 variants while maintaining the 128-bit memory bus across all three models. While the entry-level RTX 5050 model utilizes GDDR6 memory, the RTX 5060 and RTX 5060 Ti are awarded with the faster GDDR7. The consistent 128-bit interface suggests NVIDIA is leveraging memory compression technologies and GDDR7's increased bandwidth to deliver performance improvements without widening the memory bus. Each tier features a slight increase in CUDA core count, a modest boost over the previous generation RTX 40 series. With the RTX 5050 targeting 1080p gaming, the RTX 5060 is positioned for high-refresh 1080p and entry-level 1440p, and the RTX 5060 Ti is likely aimed at solid 1440p performance across most titles. While we don't know the exact release date, we can expect to hear more about the availability in the coming weeks.



View at TechPowerUp Main Site | Source

 

[oxrufiioxo]

The 3 best selling gpu's from this generation all trash. #Progress.

I can't wait to see the pricing hijinks on these.

 

[Shtb]

1440p:

... 7800XT
... 5060Ti (4608 FP32 cores)
... 7700XT

 

[docnorth]

5060 ti should be around 4070 performance. With a MSRP of 450-480$ and real pricing 100$ higher many people will keep their GPUs longer.
Best (or worst) part, during black Friday offers I could find a 4070 at 549€ and 4070 super at 579€.

 

[JustBenching]

The 3 best selling gpu's from this generation all trash. #Progress.

I can't wait to see the pricing hijinks on these.

I'm hopeful. Power draw seems way up, hope it translates to performance.

 

[Dristun]

5060ti will be a more efficient 3080 with 16GB. For $449 it would be fine. As for the other two I'll pretend they don't exist.

 

[AusWolf]

More GBxxx-250 and -300 chips. Retaining the -400 fully enabled die for the Super cards (and an artificial supply limit), woohoo!

 

[boomheadshot8]

So
4060 has 3072/96/48 8 Go G6 126 bits
4060 ti has 4352/136/48, 8/16 Go G6 128bits
4070 has 5888/184/64 , 12 Go G6X 192 bits

5050 lower perf than 4060 ?
i expect the 5060ti behind 4070 and little ahead 4060ti

 

[mama]

Anything with 8GBs is DOA, unless it's under $150.

 

[tfdsaf]

Garbage cards. 5060 seems like 4060ti performance, will likely cost $300, its 100% DOA!

The 5060ti with the modest shaders uplift over the 4060ti is likely to be 10% faster, so another DOA card!

 

[boomheadshot8]

If the games engines was more efficient and optimised you could run some game at 4k with 8GBs VRAM at 60fps for ~300$

 

[Nostras]

5050 can be good if the price is right.

5060 and 5060Ti sadden me as Nvidia is most definitely not going to price them well, still stuck with 8GB on the low end.
Can't wait for AMD to do the exact same thing.

 

[mate123]

My 3060 ti stays relevant longer then ... the castrated 128 bit bus is just insulting...

 

[dj-electric]

My 3060 ti stays relevant longer then ... the castrated 128 bit bus is just insulting...

Would having it at 192BIT bus and reducing the memory speed to those of GDDR6 type make you feel better?

 

[Onasi]

People calling these cards DOA are putting the cart before the horse. Same was said about the “pathetic” and “castrated” and “glorified 4050” RTX 4060 and, to the surprise of absolutely nobody, it’s the top selling GPU of 40 series. So no, if these cards actually get decent enough supply and avoid TOO MUCH of the current pricing nonsense they will absolutely sell well. If not, well, they will just join the club of other DOA (for various reasons) cards. Which is EVERY CARD this generation in terms of value for the gamer customers.

 

[dismuter]

My 3060 ti stays relevant longer then ... the castrated 128 bit bus is just insulting...

What's insulting is that this has still less RAM than a plain 3060 that came out 4 years ago. Even more insulting for the 8 GB Ti because the 3060 was a lower price tier.

Would having it at 192BIT bus and reducing the memory speed to those of GDDR6 type make you feel better?

Actually the 192-bit bus would at least give us 12 GB of RAM, which would be the minimum decent amount for the $400-$500 Ti models.
(Sure, they could also do 12 GB with the 128-bit bus now that 3 GB modules exist, but I assume that they're too expensive)

 

[AusWolf]

People calling these cards DOA are putting the cart before the horse. Same was said about the “pathetic” and “castrated” and “glorified 4050” RTX 4060 and, to the surprise of absolutely nobody, it’s the top selling GPU of 40 series. So no, if these cards actually get decent enough supply and avoid TOO MUCH of the current pricing nonsense they will absolutely sell well. If not, well, they will just join the club of other DOA (for various reasons) cards. Which is EVERY CARD this generation in terms of value for the gamer customers.

Let's see how long the "there's no bad card just bad prices" argument still holds for 8 GB cards.

 

[Onasi]

Let's see how long the "there's no bad card just bad prices" argument still holds for 8 GB cards.

For the foreseeable future. The vast, VAST majority of PC gaming public doesn’t play games that require more VRAM. Even when they do, they shrug and drop down the settings and continue playing. The enthusiast “my 4K ultra benchmarks” bubble is hilariously out of touch.

 

[londiste]

The consistent 128-bit interface suggests NVIDIA is leveraging memory compression technologies and GDDR7's increased bandwidth to deliver performance improvements without widening the memory bus.

Not only that. I bet they are also making sure they are ready if bigger memory chips should show up. Looks like 24Gbit or 32Gbit GDDR6 or GDDR6X will not happen but GDDR7 ones are on roadmap and reportedly 24Gbit ones coming later this year.

 

[Denver]

For the foreseeable future. The vast, VAST majority of PC gaming public doesn’t play games that require more VRAM. Even when they do, they shrug and drop down the settings and continue playing. The enthusiast “my 4K ultra benchmarks” bubble is hilariously out of touch.

It's not about the 4K ultra settings; it's about people advocating against low-end hardware being stuck with the same VRAM capacity as the RX 480 had a decade ago. This limitation not only holds back the baseline quality that studios aim for but also impacts the industry's progress. While problematic games with only 8GB VRAM do exist, they remain exceptions rather than the rule, precisely because of that.


It's absolutely baffling how 8GB renders Nvidia's own marketing for the frame generator even more ineffective. lol

 

[Onasi]

@Denver
What are you even talking about? First of all, bitching on the forums isn’t “advocating” for or against anything - no company will care. Secondly, let me reiterate - the vast majority of PC gamers play games that don’t CURRENTLY require more VRAM and won’t really EVER do so. There is no “progress” that’s being hindered here, games like LoL or CS or Rocket League or various MMOs just don’t really scale with VRAM, there’s no holding back happening there. As for the AAA titles, what VRAM PC dGPUs have is irrelevant - their progress and technical level is determined solely by console hardware and has been for a long time.

Look, I actually fundamentally agree with you and do think that just from the perspective of advancing forward we need to get more VRAM in the mainstream segment. But the issue is here is that for the actual companies making the card there is no logical incentive to do so and the market also doesn’t really push for it. So, yeah.

 

[Broken Processor]

Anything with 8GBs is DOA, unless it's under $150.

Won't happen because ram is only a small cost to the overall product they simply should be 12gb minimum but they won't do that because of artificial product segmentation. Even 12gb at 1080p is going to be tested in some games.

 

[Bwaze]

People calling these cards DOA are putting the cart before the horse. Same was said about the “pathetic” and “castrated” and “glorified 4050” RTX 4060 and, to the surprise of absolutely nobody, it’s the top selling GPU of 40 series. So no, if these cards actually get decent enough supply and avoid TOO MUCH of the current pricing nonsense they will absolutely sell well. If not, well, they will just join the club of other DOA (for various reasons) cards. Which is EVERY CARD this generation in terms of value for the gamer customers.

To be fair, lots of these cards end up in pre-built PC's that aren't meant purely for gaming, but have higher capabilities of ones with only integrated GPUs. They are targeted mostly to school children here - but I think tey actually sell more of those PCs than more expensive gaming oriented ones - people that spend more often go the DIY route.

 

[Chaitanya]

A sub $200 card with encoder and decoder support as rest of Turdwell family would be quite useful.

 

[Daven]

It seems like in between bit-widths are out of style this generation. Only the 5070, B570 and B580 have in between widths.