Friday, December 27th 2024

NVIDIA GeForce RTX 5090 Features 16+6+7 Phase Power Delivery on 14-Layer PCB

Fresh details have surfaced about NVIDIA's upcoming flagship "Blackwell" graphics card, the GeForce RTX 5090, suggesting power delivery and board design changes compared to its predecessors. According to Benchlife, the new Blackwell-based GPU will feature a new 16+6+7 power stage design, departing from the RTX 4090's 20+3 phase configuration. The report confirms earlier speculation about the card's power requirements, indicating a TGP of 600 watts. This specification refers to the complete power allocation for the graphics subsystem, though the actual TDP of the GB202 chip might be lower. The RTX 5090 will ship with 32 GB of next-generation GDDR7 memory and utilize a 14-layer PCB, possibly due to the increased complexity of GDDR7 memory modules and power delivery. Usually, GPUs max out at 12 layers for high-end overclocking designs.

The upcoming GPU will fully embrace modern connectivity standards, featuring PCI Express 5.0 x16 interface compatibility and implementing a 12V-2×6 power connector design. We spotted an early PNY RTX 5090 model with 40 capacitors but an unclear power delivery setup. With additional power phases and more PCB layers, NVIDIA is pushing the power delivery and signal integrity boundaries for its next-generation flagship. While these specifications paint a picture of a powerful gaming and professional graphics solution, questions remain about the broader RTX 50 series lineup. The implementation of the 12V-2×6 connector across different models, particularly those below 200 W, remains unclear, so we have to wait for the CES-rumored launch.
Sources: Benchlife.info, via VideoCardz
Add your own comment

109 Comments on NVIDIA GeForce RTX 5090 Features 16+6+7 Phase Power Delivery on 14-Layer PCB

#76
L0stS0ul
Greed. In the end they will be left with hundreds of thousands of unsellable chips that no one will buy, even for Deep Learning :banghead: :rolleyes:
Posted on Reply
#77
TechBuyingHavoc
L0stS0ulGreed. In the end they will be left with hundreds of thousands of unsellable chips that no one will buy, even for Deep Learning :banghead: :rolleyes:
I don't think it works like that. Either people WILL buy them and the prices remain elevated, or they don't and the prices will fall until people do start buying them.
Posted on Reply
#78
TokyoQuaSaR
utilize a 14-layer PCB, possibly due to the increased complexity of GDDR7 memory modules and power delivery. Usually, GPUs max out at 12 layers for high-end overclocking designs.
This is pretty much entirely due to the pin numbers of the GPU. 512b memory bus requires a huge amount of IO. This and the huge demand for power supply current. In the end, the more rows and columns of IOs, the more layers needed, that's pretty much it.
Posted on Reply
#79
Wirko
TokyoQuaSaRThis is pretty much entirely due to the pin numbers of the GPU. 512b memory bus requires a huge amount of IO. The more rows and columns of IOs, the more layers needed, that's pretty much it.
PCIe 5.0 makes things even more complicated. Given the memory chip layout, some lanes probably run under the memory chips and/or other lanes. This is quite unfavourable because these wires require a specific geometry (distance to ground, to other lanes etc).
Posted on Reply
#80
Unregistered
RedelZaVednoHigh end as we knew it is dead. It's either "HI-FI" or "MID-FI" if we compare GPUs to headphones or speakers. Either you pay A LOT to get true high end (5090), or just a lot and get mid end, advertized as high end (5080). There is nothing in between and that's by design. Nvidia wants to be a luxury brand. I would laugh to anyone writing that GPU could be a luxury 10 years back, but here we are:confused:
Luxury brand which need to be avoided at all cost. Their marketing bubble is incredibly strong. As well-informed costumer run away.
Giving allure of buying something more expensive but better, innovative and prestigious. LIE.

Indulging in Exurban Opulence of a Modern GPUs? (>300$)

5
"HI-FI"
4090/5090 class
Premium halo product of second order UPSELL.

4
"MID-FI"
4070 Ti S class
Premium halo product first order OVERSPEND.

3
"HIGH END"
7800xt /7900 GRE/9070xt class
Way too EXPENSIVE for a toy it is, THE MORE YOU SPEND THE MORE YOU SAVE

2
"MID TIER"
6750xt/7700xt
SUFFICIENT
AMD native 1440p HDR

1
"VALUE"
ENOUGH
¬200euro used

0
"FREEDOM TIER"
PERFECT
no GPU, no gaming
healthier, wealthier, and wiser
Posted on Edit | Reply
#81
Wirko
oddrobert0
"FREEDOM TIER"
PERFECT
no GPU, no gaming
healthier, wealthier, and wiser
Ah, and you finally have enough free time for golfing, tennis, sailing and horse riding!
Posted on Reply
#82
TheinsanegamerN
Naifm92so this thing is most likely gonna cost $3000 min?

i still remember when $700 was for the top-dog, now it won't even get you mid-range xx70ti class card
I too remember a time when our money supply was LESS THEN HALF what it is today, when $40k a year was a decent wage, and we were coming out of a massive economic collapse that suppressed the cost of almost everything. I remember when a full wafer from TSMC cost $2000, not $30,000.
TechBuyingHavocI don't think it works like that. Either people WILL buy them and the prices remain elevated, or they don't and the prices will fall until people do start buying them.
Inflation is a thing, but people dont like hearing the truth. Everyone seems to think a $500 RTX 4090 is just around the corner.....
Posted on Reply
#83
AusWolf
TheinsanegamerNI too remember a time when our money supply was LESS THEN HALF what it is today, when $40k a year was a decent wage, and we were coming out of a massive economic collapse that suppressed the cost of almost everything. I remember when a full wafer from TSMC cost $2000, not $30,000.
The problem is that $40k a year is still a decent wage. Only prices have gone up, wages haven't (at least here in the UK).
Posted on Reply
#84
mb194dc
Chrispy_Business buying these up for AI means that the likely $3000 MSRP of these is going to be irrelevant, as they'll be scalped hard at launch, probably 50% more than MSRP and so hard to get your hands on one.

Yes, if you have infinite money you can throw it away on one for gaming, but the game developers are still targeting far more modest hardware and 5090 owners aren't something they're even paying any attention to.
Possible, still nothing on the front end that looks remotely like paying for the several hundred billion spent on GPUs to go in LLMs so far.

5090 is seemingly like a Titan card and will have 0.5% of the market at most.
Posted on Reply
#85
Chrispy_
mb194dcPossible, still nothing on the front end that looks remotely like paying for the several hundred billion spent on GPUs to go in LLMs so far.

5090 is seemingly like a Titan card and will have 0.5% of the market at most.
It's only the massive megacorps filling datacenters with NVL72 racks at $3M a rack before operating costs.

The other 7 million tech companies around the world who don't need datacenter-scale tech are just buying 4090s. We have a few pods of 7 GPUs in a 4U chassis, and they do happen to be be Quadros but only because we need a Quadro-specific software feature. For many ML and LLMs applications a few 4090s in 8-12U of rack space replace multiple 42U racks of traditional compute, so that's why 4090s are so expensive. The business supply wholly outstrips Nvidia's production capability, even with sanctions against the largest customer (China), so they're stupid expensive for consumers.
Posted on Reply
#86
Wirko
TheinsanegamerNI remember when a full wafer from TSMC cost $2000, not $30,000.
That was when the manufacturing cost per transistor was dropping sharply every year... now no more.
Posted on Reply
#87
Hankieroseman
oddrobertLuxury brand which need to be avoided at all cost. Their marketing bubble is incredibly strong. As well-informed costumer run away.
Giving allure of buying something more expensive but better, innovative and prestigious. LIE.

Indulging in Exurban Opulence of a Modern GPUs? (>300$)

5
"HI-FI"
4090/5090 class
Premium halo product of second order UPSELL.

4
"MID-FI"
4070 Ti S class
Premium halo product first order OVERSPEND.

3
"HIGH END"
7800xt /7900 GRE/9070xt class
Way too EXPENSIVE for a toy it is, THE MORE YOU SPEND THE MORE YOU SAVE

2
"MID TIER"
6750xt/7700xt
SUFFICIENT
AMD native 1440p HDR

1
"VALUE"
ENOUGH
¬200euro used

0
"FREEDOM TIER"
PERFECT
no GPU, no gaming
healthier, wealthier, and wiser
I remember when a '70 Hemi Challenger was $3000. New. Now they're $45,000. No I had a '67 "Cuda" 273 PowerPak ($795 used)
Posted on Reply
#88
Dawora
mb194dcPossible, still nothing on the front end that looks remotely like paying for the several hundred billion spent on GPUs to go in LLMs so far.

5090 is seemingly like a Titan card and will have 0.5% of the market at most.
5090 will be sell more than Amd 9070
TheinsanegamerNI too remember a time when our money supply was LESS THEN HALF what it is today, when $40k a year was a decent wage, and we were coming out of a massive economic collapse that suppressed the cost of almost everything. I remember when a full wafer from TSMC cost $2000, not $30,000.


Inflation is a thing, but people dont like hearing the truth. Everyone seems to think a $500 RTX 4090 is just around the corner.....
There will be time when u can get 4090 performance for 500$

just like 2080Ti performance we allredy can get cheap.
So yes 4090 for 500$ is arount the corner
Posted on Reply
#89
AusWolf
DaworaThere will be time when u can get 4090 performance for 500$

just like 2080Ti performance we allredy can get cheap.
So yes 4090 for 500$ is arount the corner
There will be a time when you're exactly one year older than you are today. Admire my wisdom. :respect:

Jokes aside, old cards on the used market was not the topic here. The post you commented on stated that people think there are fast new cards coming out soon, which will lead to disappointment.
Posted on Reply
#90
Dawora
AusWolfThere will be a time when you're exactly one year older than you are today. Admire my wisdom. :respect:

Jokes aside, old cards on the used market was not the topic here. The post you commented on stated that people think there are fast new cards coming out soon, which will lead to disappointment.
dont know what ppls are waiting for but maybe they can just pay more if they want more performance?
Posted on Reply
#91
x4it3n
Onasi@RedelZaVedno
Cool, cool. I don’t care for ravings about NGreedia, leather jackets and fake frames. I heard that before. I am sticking to my point. Again. WHAT. ARE. YOU. WILLING. TO. BET?
The 5080 "should" be on par or slightly faster than the 4090, but mostly due to better IPC, Higher Clocks and GDDR7 memory, because the extra 5% CUDA Cores are not going to do much lol.

I think the 5080 will be on par with the 4090 just like the 3070 is on par with the 2080 Ti (as long as VRAM capacity is not an issue). But I'm sure Nvidia will mostly show RT/PT benchmarks to make it look better than it is. Nvidia are definitely cheaping out on all tiers except x90 GPUs. Sad but true. We will maybe see a 5080 Ti given the huge gap with the 5090, but maybe they'll release a 5090 Ti or TITAN Blackwell too, wait and see!
Posted on Reply
#92
AusWolf
Daworadont know what ppls are waiting for but maybe they can just pay more if they want more performance?
That's a hard no. Let me give you a few numbers:

The GTX 580 launched at $499 (this will be 100% performance for our example).
The GTX 680 launched at $499 with 123% the performance of the 580 - that's a 23% better price-to-performance ratio.
The GTX 780 launched at $649 with 124% the performance of the 680 - that's a 5% price-to-performance reduction.
The GTX 980 launched at $549 with 138% the performance of the 780 - that's a 64% better p-to-p.
The GTX 1080 launched at $599 with 151% the performance of the 980 - that's a 38% better p-to-p.
The RTX 2080 launched at $699 with 139% the performance of the 1080 - that's a 20% better p-to-p.
The RTX 3080 launched at $699 with 163% the performance of the 2080 - that's a 63% better p-to-p (which was ruined by the crypto boom, but that's another story).
The RTX 4080 launched at $1,199 with 149% the performance of the 3080 - that's a 13% p-to-p reduction. The worst offer in the last 15 years of Nvidia graphics cards.

So essentially, with the GTX 780 and the RTX 4080, you're getting less for your money than you did with the last gen. You can explain a few percent price increase year-per-year over the last gen with inflation or whatnot, but there is no explanation why a 4080 should cost double than a 3080 did at launch while being only 1.5x as fast. Mind you, the 4080 launched in 2022, when inflation was 11.1%. So even with that factored in, you still got less for your money than you did with the 3080.

More performance should come from technological advancements, and not from consumers throwing money at it.
Posted on Reply
#93
Hankieroseman
TheinsanegamerNI too remember a time when our money supply was LESS THEN HALF what it is today, when $40k a year was a decent wage, and we were coming out of a massive economic collapse that suppressed the cost of almost everything. I remember when a full wafer from TSMC cost $2000, not $30,000.


Inflation is a thing, but people dont like hearing the truth. Everyone seems to think a $500 RTX 4090 is just around the corner.....
...and donald is Jesus and gas will be 99 cents a gallon again. I expect another collapse before the orangeman is done. Get your stuff early.
Posted on Reply
#96
TumbleGeorge
AusWolfThat was kind of expected. They're not pushing for the new power connector so hard for nothing.
Now we have article for this in TPU.
Presented power consumption is not for whole graphic cards. Who knows what is total consumption especially for more overclocked branded models.
Posted on Reply
#98
AusWolf
HankierosemanNatural progression of the video card. 3090 was hot! 4090 hotter and 5090 is hottest(so far).
Well, I didn't care too much about the 3090, even less about the 4090, and I'm only laughing at the 5090. Thanks, Nvidia! Keep up the good work. :roll:
Posted on Reply
#99
Hankieroseman
Ain't FREEDOM grand?
My 3090 is awesome and my 4090 is magical. I expect the 5090 to be even more fabulous than I can imagine. My simulator will love me(as soon as I get my motherboard back from ASUS Service Center, CA)
Posted on Reply
#100
Why_Me
HankierosemanNatural progression of the video card. 3090 was hot! 4090 hotter and 5090 is hottest(so far).
Posted on Reply
Add your own comment
Nov 22nd, 2026 01:28 PST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts