NVIDIA’s GeForce RTX 4090 graphics card has again been detailed in new rumored specs and it’s expected to be twice as fast as the GeForce RTX 3090.
NVIDIA GeForce RTX 4090 is said to have 16,128 cores, 24GB of memory, 21Gbps speeds, 450W TDP and twice as fast as RTX 3090
The latest specs were tweeted once again by Kopite7kimi. The NVIDIA GeForce RTX 4090 will also use the same AD102 GPU as the “Ti” variant, but in a rumored scaled-down configuration.
The AD102 “Ada Lovelace” GPU is expected to feature 144 SMs, a 71% increase over the existing GA102 GPU and house a massive 18,432 CUDA cores. The GeForce RTX 4090 GPU SKU is rumored to feature 16,128 CUDA cores, which is a 50% increase in core count over the RTX 3090, but 14% fewer cores than the full AD102 configuration that might be coming. later as RTX 4090 Ti. It’s the same situation this generation where the “Ti” variant of the 3090 got the full GA102 GPU and the non-Ti variant, although launched earlier, came with a reduced configuration.
Alright, let’s do a recap.
RTX 4090, AD102-300, 16128FP32, 21Gbps 24G GDDR6X, 450W, ~2×3090.
I am disappointed with RDNA3.
– kopite7kimi (@kopite7kimi) May 16, 2022
In addition to SM count, Ada Lovelace GPUs will also feature increased L2 cache sizes. Starting with the AD102 GPU, the flagship is said to be equipped with up to 96MB of L2 cache, a crazy 16x increase from the 6MB L2 cache featured on GA102. This cache still isn’t as large as the Infinity Cache featured on AMD’s RDNA cards, but it’s still a huge leap forward for NVIDIA’s own graphics cards.
The NVIDIA GeForce RTX 4090 graphics card will also rock 24GB of GDDR6X memory clocked at 21Gbps on a 384-bit bus interface and delivering over 1.0TB/s bandwidth. The final details also tone down the overall TDP numbers to 450W, meaning the RTX 4090 can’t go crazy with the clocks the full-fat variant with a 600W would have to go with.
As we saw with the GeForce RTX 3090 Ti, there are some models that go beyond the 450W TBP (reference) and up to 516W (custom). The same goes for cards based on Ada Lovelace. And while it will take a lot of cooling, it looks like the AIBs are well on their way. We will likely see the use of more hybrid style GPU coolers rather than traditional air coolers once we get past the 600W TBP limit. This will mark a 33% increase in TBP over the RTX 3090 Ti. According to the latest rumors, NVIDIA is expected to announce its next-gen GeForce RTX 40 series by mid-July, which means we’ll be receiving a new generation of cards in early Q3 2022.
NVIDIA GeForce RTX 40-series graphics card lineup (rumored):
|Graphic card||GPUs||PCB variant||SM Units / Hearts||Memory / Bus||Memory Clock / Bandwidth||TGP||Power connectors|
|NVIDIA GeForce RTX 4090Ti||AD102-350?||To be determined||144 / 18432?||48 GB / 384 bit||24 Gbit/s / 1.15 TB/s||~600W||1x 16 pin|
|NVIDIA GeForce RTX 4090||AD102-300?||PG137/139 UGS330||126 / 16128?||24 GB / 384 bit||21 Gbps / 1.00 TB/s||~450W||1x 16 pin|
|NVIDIA GeForce RTX 4080||AD103-300?||To be determined||>84 / 10752?||16 GB / 256 bit||21 Gbit/s / 672 GB/s||~350W||1x 16 pin|
|NVIDIA GeForce RTX 4070||AD104-400?||PG141-310 SKU341||>60 / 7680||12 GB / 192 bit||18 Gbit/s / 432 GB/s||~300W||1x 16 pin|
#NVIDIA #GeForce #RTX #GPU #Specs #cores #24GB #21Gbps #GDDR6X #memory #450W #TDP #fast #RTX