VideoCardz has published a leaked slide presumably from Nvidia's final presentation of its GeForce RTX 4070 graphics card. The slide reveals a final price of the add-in-board as well as some of its specifications. In particular, it says that the product will cost $599 and will have a total graphics power of 200W.
Nvidia is expected to release its GeForce RTX 4070 graphics card in mid-April, but most of its specifications have been known for some time, albeit not from the company itself. The upcoming vanilla version of Nvidia's GeForce RTX 4070 shares the AD104 graphics processor with the RTX 4070 Ti, but has only 5888 CUDA cores operating at 1920 MHz – 2475 MHz. Just like the 'Titanium' version, the GeForce RTX 4070 features a 12GB GDDR6X memory subsystem with a 192-bit interface.
The new graphics card is said to have a total graphics power of 200W, which is significantly lower than the TGP of Nvidia's GeForce RTX 4070 Ti (285W) and GeForce RTX 3070 Ti (290W). This would enable graphics cards makers to miniaturize cooling systems of the GeForce RTX 4070 and therefore maximize compatibility with more compact computer cases, which will be another reason why this board will likely enter the ranks of one of the best graphics cards available. Idle power and video playback power of the new board will also be lower compared to that of its predecessors, according to the slide.
Despite having a heavily cut-down AD104 GPU, the GeForce RTX 4070 is expected to produce approximately 29 FP32 TFLOPS of computational power, which is comparable to that of the GeForce RTX 3080. However, the RTX 3080 possesses a 320-bit memory bus and an impressive peak bandwidth of 760 GB/s, which is substantially greater than the 504 GB/s bandwidth provided by AD104's 21 GT/s GDDR6X memory. In fact, even a GeForce RTX 3070 Ti has higher memory bandwidth (608 GB/s) than the newcomer. Meanwhile, the new graphics card is supposed to have a large L2 cache, which will likely compensate for a slower memory subsystem.
|Row 0 - Cell 0||GPU||FP32 CUDA Cores||Memory Configuration||TBP||MSRP|
|GeForce RTX 4090 Ti||AD102||18176 (?)||24GB 384-bit 24 GT/s GDDR6X (?)||600W (?)||?|
|GeForce RTX 4090||AD102||16384||24GB 384-bit 21 GT/s GDDR6X||450W||$1,599|
|GeForce RTX 4080||AD103||9728||16GB 256-bit 22.4 GT/s GDDR6X||320W||$1,199|
|GeForce RTX 4070 Ti||AD104||7680||12GB 192-bit 21 GT/s GDDR6X||285W||$799|
|GeForce RTX 4070*||AD104||5888 (?)||12GB 192-bit 21 GT/s GDDR6X||250W (?)||?|
|GeForce RTX 4060 Ti*||AD106||4352 (?)||8GB 128-bit 18 GT/s GDDR6||160W (?)||<$500?|
|GeForce RTX 3070||GA104||5888||8GB 256-bit 14 GT/s GDDR6||220W||$499|
Perhaps an interesting wrinkle of the slide is that Nvidia compares its GeForce RTX 4070 graphics card to its previous-generation GeForce RTX 3070 and RTX 3070 Ti offerings. With its Ada Lovelace GPUs, Nvidia has been emphasizing that its latest GPUs can rival or surpass higher-class previous-generation offerings at lower price. With its GeForce RTX 4070, it looks like Nvidia is betting on higher-performance and lower power at the same launch price.
In any case, Nvidia has not announced its GeForce RTX 4070 officially and we cannot verify authenticity of the slide. Therefore, take the information with a grain of salt for now.
Edit: As noted below in shear terms of cost per frame the RTX 4070 Ti does indeed hold the "best bang for buck" title among the available 4000 series cards. By saying feeling the 4090 has better bang for the buck I meant for that 100 dollars more on each you get 3090->4090 = 65% performance increase VS 3070 Ti-> 4070 Ti = 50% performance increase. Thus 100 dollars more for 65% increase feels more worth it compared to 100 dollars more for 50%. But the steep performance drop off for Nvidia cards as you go down the stack does predate the 4000 series by a fair number of generations.
So while it might feel like the 4090 has the better price/performance, that isn't actually correct. Especially since more and more 4070Ti crop up for below MSRP here where I live. The 4070 will most likely be even better price/performance and possibly better performance/watt as well. But we will have to wait for the 3rd party testing to be sure.
I am aware thus why I said feels like and not is (ie overall performance uplift compared to cost increase for each 65% vs 50% for 100 US) though I could have been more clear on my why I will edit my post... and until the RTX 4070Ti dropped the 4090 did indeed have a better price peformance compared to the 4080 which was insane. Something I have not seen happen before in a flagship card. And despite beating the 4090 in bang for buck...the 4070Ti is still woefully overpriced, which was generally my point for all Nvidia GPUs this gen. Not to mention the performance of both the 4080 and 4070 Ti are also underpowered by about 10-15% each. IMHO at least...All in all I have been less than satisfied with this gen. But I also think Nvidia and AMD will course correct in time with prices which could change the conversation considerably.
What's with Nvidia forcing every single product into the "no man's land" pricing between $500 and their halo product?
If you have $600 for something as completely unnecessary as "slightly prettier" gaming graphics (but only when viewed on a high end monitor), then you have $1200. If you have $1200, then price is no object.
If you want to sell us absurdly overpriced GPUs, then leather granddaddy should at least even pretend to give us a reason. Where are the games?
Everybody has already figured out that you can't make money with these GPUs. Streaming is rigged and mining is dead, so what does GPU performance even matter, at this point?
The 2070 didn't even get close to beating the 1080Ti. It barely beat the regular 1080 by a single digit percentage.
From what I dug up online, the 1070 was less than 5% better than the 980Ti and the 3070 again didn't quite reach the 2080Ti. So yes, plenty of time.
Your argument makes no sense. Someone willing or able to pay 800 USD might not be able or willing to 900, 1000, or especially 1200. That is utter bs. Also, with the current trend, with that stance you will never buy a GPU again, be it Nvidia or AMD. Who, I want to point out, is just as bad with their pricing. Biiiiiig surprise (not).