Friday, June 19th 2020
Possible NVIDIA GeForce RTX 3090, RTX 3080, and "TITAN Ampere" Specs Surface
Alleged specifications of NVIDIA's upcoming GeForce RTX 3090, RTX 3080, and next-generation TITAN graphics cards, based on the "Ampere" graphics architecture, surfaced in tweets by KatCorgi, mirroring an early-June kopite7kimi tweet, sources with a high hit-rate on NVIDIA rumors. All three SKUs will be based on the 7 nm "GA102" silicon, but with varying memory and core configurations, targeting three vastly different price-points. The RTX 3080 succeeds the current RTX 2080/Super, and allegedly features 4,352 CUDA cores. It features a 320-bit GDDR6X memory interface, with its memory ticking at 19 Gbps.
The RTX 3090 is heir-apparent to the RTX 2080 Ti, and is endowed with 5,248 CUDA cores, 12 GB of GDDR6X memory across a 384-bit wide memory bus clocked at 21 Gbps. The king of the hill is the TITAN Ampere, succeeding the TITAN RTX. It probably maxes out the GA102 ASIC with 5,326 CUDA cores, offers double the memory amount of the RTX 3090, at 24 GB, but at lower memory clock speeds of 17 Gbps. NVIDIA is expected to announce these cards in September, 2020.
Sources:
KatCorgi (Twitter), VideoCardz
The RTX 3090 is heir-apparent to the RTX 2080 Ti, and is endowed with 5,248 CUDA cores, 12 GB of GDDR6X memory across a 384-bit wide memory bus clocked at 21 Gbps. The king of the hill is the TITAN Ampere, succeeding the TITAN RTX. It probably maxes out the GA102 ASIC with 5,326 CUDA cores, offers double the memory amount of the RTX 3090, at 24 GB, but at lower memory clock speeds of 17 Gbps. NVIDIA is expected to announce these cards in September, 2020.
58 Comments on Possible NVIDIA GeForce RTX 3090, RTX 3080, and "TITAN Ampere" Specs Surface
Titan is for have performance crown
Maybe a tweet isnt long enough for it.
I was seriously considering plunking down for a Titan this generation.
Calculations were based on RTX 2xxx lineup configuration (number of SMs and GPCs) and they were scaled to the specs of GA100 GPU (see below). FP32 TFLOPs were calculated assuming 2 GHz base clock. I'm not sure about the specs of RTX 3070S, so I've included two possible versions.
Here is the configuration of fully enabled GPUs:
Anyways, these some of the least credible specs that I've seen.
also,seens nvidia leave bank alot cores,near 3000! max cores numbers are over 8000,yes, you read right.
big navi.. i seen it again...errh, and it cant get even near rtx 3090...what dream world some2 live?
amd cant beat now even 12nm rtx 2070 super OC gpu, and then its still must beat its four big brother..,there is enough to job legendary big navi.
also, we all KNOW fact that big navi is still 7nm gpu with nothing new special upgrade...remembe this, i bet that big navi is watercooled gpu....still i cant belive it, these days..
sure im sure it should beat now old 16nm gtx 1080 ti OC gpu..hmm, must...but remembe check it tdp and efficiency.
well 'my' leak it small, and i warn amd fans,dont except it anyhting what it CANT be, rtx 3070 is too much it.
anyway,competition is always good,you will seen both september and october. nvidia and amd.
btw, i wait also intel high end gpu...exiting...
great weekends all!
Cause while I cut use more gpu power for true 4K fun, 1080 Ti is no slug either yet. As far I have seen 1080 TI performance much like a RTX 2070 SUPER more or less. So cut use more power, but are not in a desperate need either. I can live with 1440P for a while yet if I have to.
Btw, if these are real specs, I suspect a Ti or SUPER version coming for each tier later on, as none of these specs seem to operate with fully enabled GPUs. But using the same GPU for 3 tiers seems unlikely to say the least (unless production is really that bad).