• Ever wanted an RSS feed of all your favorite gaming news sites? Go check out our new Gaming Headlines feed! Read more about it here.

Dakhil

Member
Mar 26, 2019
4,459
Orange County, CA
videocardz.com

Geekbench leak confirms NVIDIA GeForce RTX 3070 Mobile features 5120 CUDA cores - VideoCardz.com

According to Geekbench benchmark results that were posted by APISAK today, the RTX 3070 Mobile GPU will indeed have 5120 CUDA Cores. NVIDIA GeForce RTX 3070 Mobile with 5120 CUDA cores The new laptop GPU is listed with 40 Compute Units, which in this case refers to NVIDIA Streaming...
The new laptop GPU is listed with 40 Compute Units, which in this case refers to NVIDIA Streaming Multiprocessors. Each Ampere SM carries 128 CUDA cores, thus in total, the GPU features 5120 CUDA cores.

NVIDIA GeForce RTX 3070 Mobile appears to have 8GB GDDR6 memory, which is not unexpected considering that the GA104 GPU this card is equipped with has a 256-bit memory bus. It is unclear if this variant which was found in HP Omen 15 laptop is a Max-P or Max-Q variant, but judging from the maximum GPU frequency that this card has achieved during the test, it should be a power-limited Max-Q variant.

It would appear that the GPU scored 101621 and 110839 points in two separate tests, which puts it between desktop GeForce RTX 2080 and RTX 2080 SUPER series based on Turing architecture.

 

Issen

Member
Nov 12, 2017
6,813
I was honestly expecting a somewhat higher performance jump going from 2070 Max-Q to 3070 Max-Q. But it's decent enough, I guess.
 

Tizoc

Member
Oct 25, 2017
23,792
Oman
All this tells me is that it has 3 times the cuda cores of my GTX 970M, non the less really looking forward to CES in 2 weeks time to see how the new mobile GPUs gonna be @3@
 

hyouko

Member
Oct 27, 2017
3,206
My gaming laptop just died (ironically, appears to have been killed by a shitty cooling pad that drew too much power over USB). Will be watching with interest.
 

FrakEarth

Member
Oct 25, 2017
3,271
Liverpool, UK
It would appear that the GPU scored 101621 and 110839 points in two separate tests, which puts it between desktop GeForce RTX 2080 and RTX 2080 SUPER series based on Turing architecture.

The article mentions the Omen 15 - high end of sub £2k laptops - it'll be wild seeing these in person. Are these laptops essentially capable of next gen quality gaming on the go?
 

Imitatio

Member
Feb 19, 2018
14,560
Nice, interested to see what the new Omen 15 looks and performs like. The 2020 models are some of my personal favourites alongside the RP-15/XMG Core 15.
 

Issen

Member
Nov 12, 2017
6,813
The article mentions the Omen 15 - high end of sub £2k laptops - it'll be wild seeing these in person. Are these laptops essentially capable of next gen quality gaming on the go?
Yes, especially if you don't plan to push for higher resolutions (1080p looks great with a 15 inch display size). When connected to a 4k TV it should still provide an experience very similar to next gen consoles as well.
 
VideoCardz: "NVIDIA GeForce RTX 3080 Mobile confirmed with 6144 CUDA cores and 16GB of memory"
OP
OP
Dakhil

Dakhil

Member
Mar 26, 2019
4,459
Orange County, CA
videocardz.com

NVIDIA GeForce RTX 3080 Mobile confirmed with 6144 CUDA cores and 16GB of memory - VideoCardz.com

NVIDIA GeForce RTX 3080 Mobile with 6144 CUDA cores A new leak featuring yet unreleased ASUS ROG Zephyrus Duo (GX551QS) laptop confirms that the flagship GeForce RTX 3080 graphics card will indeed have the full GA104 GPU. The upcoming NVIDIA Ampere based graphics card will feature 6144 CUDA...
A new leak featuring yet unreleased ASUS ROG Zephyrus Duo (GX551QS) laptop confirms that the flagship GeForce RTX 3080 graphics card will indeed have the full GA104 GPU. The upcoming NVIDIA Ampere based graphics card will feature 6144 CUDA cores and up to 16GB of GDDR6 memory.

ASUS ROG Zephyrus Duo laptop also features AMD's Ryzen 9 5900H CPU which is an 8-core and 16-thread model with a reported base clock of 3.3 GHz and 4.54 GHz boost clock. The product is equipped with a total of 48GB of DDR4-3200 memory (probably 16GB soldered with an additional 32GB memory module).

The graphics card appears with a GPU clock at 1.54 GHz, which might confirm it's a Max-Q variant specifically for this ASUS ROG laptop. With such a clock speed, the RTX 3080 Mobile scored 139181 points, which is just slightly more than the desktop RTX 3070. The desktop variant of the RTX 3080 still appears to offer 129% performance of the mobile SKU, however, the desktop card is based on a GA102 GPU processor.

 

Philippo

Developer
Verified
Oct 28, 2017
7,899
Question for those more informed: do we know if Nvidia is planning for a more up-to-date successor to the gtx 1650 max-q, or something that will cover the same range of performance in future laptops?
 
VideoCardz: "NVIDIA GeForce RTX 3080 Max-Q specifications emerge, 6144 CUDA cores clocked at 1245 MHz"
OP
OP
Dakhil

Dakhil

Member
Mar 26, 2019
4,459
Orange County, CA
videocardz.com

NVIDIA GeForce RTX 3080 Max-Q specifications emerge, 6144 CUDA cores clocked at 1245 MHz - VideoCardz.com

Further confirmation on flagship Ampere GeForce graphics card. NVIDIA GeForce RTX 3080 Max-Q: 6144 CUDAs and 12 Gbps memory Next week NVIDIA is set to announce its GeForce RTX 30 mobile graphics cards based on its 8nm Ampere architecture. The company is planning three SKUs which will be divided...
Next week NVIDIA is set to announce its GeForce RTX 30 mobile graphics cards based on its 8nm Ampere architecture. The company is planning three SKUs which will be divided into numerous variants based on their power limitations: RTX 3080, RTX 3070, and RTX 3060.

The GeForce RTX 3080 Mobile is the flagship SKU which will feature a full-fat GA104 GPU with 6144 CUDA cores. That is far fewer cores than the desktop RTX 3080 model (8704), but still more than the desktop RTX 3070 featuring GA104 GPU (5888). Therefore, it is safe to assume that desktop and mobile variants of the RTX 3080 will not offer the same performance. The performance gap between GA104 and GA102 based SKUs might be slightly confusing to customers, but not as confusing as Max-Q and Max-P SKU segmentation.

NVIDIA GeForce RTX 3080 Mobile will launch in two main variants, the Max-P with the power of a total graphic reaching 150W and the Max-Q variant which is expected to be limited to 90 or so watts. While both cards carry the same model name, they will offer different performance. The Max-P variant is expected to feature an 1110 MHz base clock and a 1545 MHz boost clock, while the Max-Q variant should offer 780 MHz and 1245 MHz respectively by default. The 'default' is a key word there since both power variants will also be further adjusted by notebook makers, so there will be many subvariants such as 80W, 115W, 125W, etc. As a result, any direct comparison between GeForce RTX 3080 variants shall list TGP values as well, otherwise, it wouldn't be a proper comparison. Fortunately, many notebook reviewers have already noticed how important this is and we are seeing more and more tests with TGP listed in the benchmark charts. Hopefully, notebook makers will list discrete GPU graphics power in their specs sheets as well.

It seems that RTX 3080 Mobile will be offered with either 16GB or 8GB memory capacity, which will segment this model even further. In reality, we might see as many as 10 models called RTX 3080 Mobile/Laptop, but each carrying a different clock speed, power limit, or memory capacity.

The RTX 3080 Max-Q features 6144 CUDA cores, 192 Texture Units, and 96 ROPs (the GPU-Z software incorrectly reports on 512 TMUs). The CPU has been submitted to the database yesterday. It appears that the Gigabyte laptop tested does not support PCIe Gen4, thus is it likely based on the Intel 10th Gen Core Comet Lake-H series. Only Tiger Lake-H will support PCI Gen4, but these are not expected till the next quarter.
 
Apr 4, 2018
4,508
Vancouver, BC
I was honestly expecting a somewhat higher performance jump going from 2070 Max-Q to 3070 Max-Q. But it's decent enough, I guess.

That is a huge jump. You'd be going from essentially GTX 1070/GTX 1660ti performance to GTX 1080ti/RTX 2080 beating performance in a laptop. It would be like having a portable Xbox Series X.

Being able to push 4k60 on Xbox One tier games is pretty amazing for a laptop. This is also the Max-Q variant, which means a proper mobile 3070 variant could potentially be even better.
 
Last edited:

RAWRferal

Member
Oct 27, 2017
1,359
London, UK
Some of you are honestly expecting too much.

Considering the physical size difference between a desktop GPU and a mobile one - this is great.

As I've said before, notebook/laptop GPUs have come a long way in the past 5 years or so.
 

Issen

Member
Nov 12, 2017
6,813
That is a huge jump. You'd be going from essentially GTX 1070/GTX 1660ti performance to GTX 1080ti/RTX 2080 beating performance in a laptop. It would be like having a portable Xbox Series X.

Being able to push 4k60 on Xbox One tier games is pretty amazing for a laptop. This is also the Max-Q variant, which means a proper mobile 3070 variant could potentially be even better.
In terms of raw performance, perhaps. But I suspect given the quality of some ports some games will struggle running console-equivalent settings in a few years. That's why I was hoping for a bit of extra performance, to have some leeway.
 

Ra

Rap Genius
Moderator
Oct 27, 2017
12,198
Dark Space
Question for those more informed: do we know if Nvidia is planning for a more up-to-date successor to the gtx 1650 max-q, or something that will cover the same range of performance in future laptops?
That'd be the RTX 3050 which is rumored to be revealed alongside the 3060 at CES.
 

X05

Member
Oct 25, 2017
868
videocardz.com

NVIDIA GeForce RTX 3080 Max-Q specifications emerge, 6144 CUDA cores clocked at 1245 MHz - VideoCardz.com

Further confirmation on flagship Ampere GeForce graphics card. NVIDIA GeForce RTX 3080 Max-Q: 6144 CUDAs and 12 Gbps memory Next week NVIDIA is set to announce its GeForce RTX 30 mobile graphics cards based on its 8nm Ampere architecture. The company is planning three SKUs which will be divided...
Man, even if that's a bit better than I was expecting for a 3080 (I thought we'd get a 3070 in all but name at most), it makes me miss the Pascal days when notebook and desktop had parity
 
Apr 4, 2018
4,508
Vancouver, BC
In terms of raw performance, perhaps. But I suspect given the quality of some ports some games will struggle running console-equivalent settings in a few years. That's why I was hoping for a bit of extra performance, to have some leeway.

Console games will always get special optimizations, but I don't expect console PC ports to get worse than they are now.

With DLSS 2.0 and significantly better ray tracing in a laptop, I'm sure even this Max-Q card will handily beat console performance most of the time, especially if Ray Tracing support keeps growing (Series X actually has slightly below RTX 2060 Super Ray tracing performance according to Digital Foundry's Watch Dogs Legion comparison). Of course, if MS' DirectML powered Super Resolution feature they are working with AMD on is successful, they may close the gap with DLSS somewhat.

Also, I should mention that the percentages in that article seem a bit off from my experience. I compared some of these numbers to Passmark, and according to that, the gap between 2080ti and 2080 performance is much smaller (i.e. better), than the gap between a 2070 and a 2070 max-Q.


Passmark Performance comparisons

2080 to 2080 max-Q - 28% dif
2080 ti to 2080 - 14% dif
2070 to 2070 max-q - 26% dif

Of course, unless you need a slim laptop, I'm sure the standard 3070 mobile card will perform even better, depending on the cooling system in the laptop itself, so perhaps wait for that. I'd still call a 14-24% performance difference between a desktop card which can afford much better cooling and a laptop Max-Q variant quite impressive. Given how much power the 3000 cards draw, I actually probably would have expected worse. This seems like it might be a better performance difference than the 2000 series had, and closer to the great performance of the GTX 10-series mobile cards. Assuming this article is correct, and this card actually does 2080-tier performance.

Also remember that while the consoles seem to be getting 2080-tier performance, thier actual real-world performance is probably a bit lower. The Radeon VII would probably be a better comparison.
 
OP
OP
Dakhil

Dakhil

Member
Mar 26, 2019
4,459
Orange County, CA

Gestault

Member
Oct 26, 2017
13,353
The RTX 2070 Max-Q is/was already pretty darn beefy for a 1080p@144hz laptop, assuming the thermals were balanced on the build.
 

Ra

Rap Genius
Moderator
Oct 27, 2017
12,198
Dark Space
I think the rumours were talking about RTX 3050 for PCs since Gigabyte's apparent listing seems to suggest that the RTX 3060 is the entry level Ampere GPU for laptops releasing in 2021.

And XMG's recent press release seems to suggest that Nvidia's still manufacturing GTX 1650 GPUs for laptops releasing in 2021.
I wouldn't use Gigabyte for the floor, as the brand doesn't make budget laptops.

Nvidia has never withheld its budget GPU from the laptop market, that'd be literally unprecedented. It's where they make the most money.