Wednesday, September 14th 2022
NVIDIA RTX 4080 12GB and 16GB Based on Different Chips, Vastly Different Shader Counts
When we first got news about NVIDIA's upcoming GeForce RTX 4080 "Ada" coming in 12 GB and 16 GB variants, we knew there was more setting the two apart than just memory size and memory bus-width. Turns out there's a lot more. According to detailed specifications leaked to the web, while the 16 GB variant of the RTX 4080 is based on the same AD103, the second largest chip after the AD102; the 12 GB RTX 4080 is based on the smaller AD104 chip which has a physically narrower memory bus.
It looks like NVIDIA is debuting the RTX 40-series with at least three models—RTX 4090 24 GB, RTX 4080 16 GB, and RTX 4080 12 GB. The RTX 4090 is the top-dog part, with the ASIC code "AD102-300-xx." It's endowed with 16,384 CUDA cores, a boost frequency of up to 2.52 GHz, 24 GB of 21 Gbps GDDR6X memory, and a typical graphics power (TGP) of 450 W, which is "configurable" up to 600 W. The RTX 4080 16 GB is based on the AD103-300-xx" comes with 9,728 CUDA cores, a boost frequency of 2.50 GHz, and 16 GB of 23 Gbps GDDR6X memory across a narrower memory bus than the one the RTX 4090 comes with. This card reportedly has a 340 W TGP configurable up to 516 W.The GeForce RTX 4090 12 GB is positioned a notch below its 16 GB namesake, but is based on the smaller AD104 chip, with 7,680 CUDA cores running at speeds of up to 2.61 GHz, 12 GB of 21 Gbps GDDR6X memory, and a TGP of 285 W that's configurable up to 366 W. It's interesting how the leak includes not just TGP, but also maximum configurable TGP. The various board partners will utilize the latter as their power limits to achieve overclocked speeds. Even the NVIDIA Founders Edition board is technically "custom design," and so it could feature higher-than-stock TGP.
Source:
VideoCardz
It looks like NVIDIA is debuting the RTX 40-series with at least three models—RTX 4090 24 GB, RTX 4080 16 GB, and RTX 4080 12 GB. The RTX 4090 is the top-dog part, with the ASIC code "AD102-300-xx." It's endowed with 16,384 CUDA cores, a boost frequency of up to 2.52 GHz, 24 GB of 21 Gbps GDDR6X memory, and a typical graphics power (TGP) of 450 W, which is "configurable" up to 600 W. The RTX 4080 16 GB is based on the AD103-300-xx" comes with 9,728 CUDA cores, a boost frequency of 2.50 GHz, and 16 GB of 23 Gbps GDDR6X memory across a narrower memory bus than the one the RTX 4090 comes with. This card reportedly has a 340 W TGP configurable up to 516 W.The GeForce RTX 4090 12 GB is positioned a notch below its 16 GB namesake, but is based on the smaller AD104 chip, with 7,680 CUDA cores running at speeds of up to 2.61 GHz, 12 GB of 21 Gbps GDDR6X memory, and a TGP of 285 W that's configurable up to 366 W. It's interesting how the leak includes not just TGP, but also maximum configurable TGP. The various board partners will utilize the latter as their power limits to achieve overclocked speeds. Even the NVIDIA Founders Edition board is technically "custom design," and so it could feature higher-than-stock TGP.
66 Comments on NVIDIA RTX 4080 12GB and 16GB Based on Different Chips, Vastly Different Shader Counts
My reply had no snark, your original post had no :p either.
Get the good word out there I guess.
Personally those gamers are better off on a PS5/SeriesX
Edit. On a 2-400 product I'm with you but on a 700+ one I don't feel bad for people who make bad decisions. Especially whole system purchases that likely cost 1500-2000 usd. I also told countless people not to buy the 1060 3GB most didn't listen stating 3GB is plenty for 1080p...
I don't even know if the differences will even show up on sites like PCGamer. Their tech editor is mostly clueless about tech. He once stated in a review on a GTX 690 that it would give better 4K performance because it had twice as much VRAM.
I only see the two 4080s as being an issue if they are priced the same or at least very close in price. I doubt that will be the case the specs are pretty different. I'm also not convinced this isn't an oem only varient where 300+ watt cards are a bad idea as it is.
This isn't the same situation as with the 1030 that came in both ddr4 and Gddr5 varients that costed about the same and performed very different that preyed on the market that would be most impacted by this.
Because I expect the 16GB to be out and reviewed first.
Then they ship the LESS performance part with increased customer excitement for the slightly cheaper one.
Hopefully W1zzard will straighten it all out for people, but I will shit in the thread if I am right and the 12GB is slightly delayed.
Because that's a scum tactic.
None of these companies are our friend they are simply here to make money so really it comes down to how good a product both varients are not what they're named hopefully they both end up decent products without highly inflated prices vs 30 series.
The case's people have now, a lot of them are not going to work well with 800watts under load in use.
There's going to be a glut of random restarts etc too, since many will chance they're future proof 850watt PSU can do it, and some can't.
My 3080ti actually runs pretty cool at 450w maxed out power limits 65-70C but I doubt 600W is realistically doable though. I still might try lol.
In addition, it sets Nvidia up for pulling more shenanigans in the future. PC gamers might have to worry about 4080s and future generations of cards with significant differences in performance despite the name suggesting they are the reasonably the same. If people don't flag this now there's nothing stopping Nvidia from bifurcating other SKUs and potentially increasing the gap in performance between said SKUs.
I really hope PC gamers put their foot down because this kind of trend only hurts consumers.