NVIDIA GeForce RTX 4090 Graphics Card Almost Twice As Fast As RTX 3090 In 3DMark Time Spy Extreme Benchmark, Alleges Rumor

NVIDIA’s GeForce RTX 4090 graphics card reportedly offers nearly twice the performance of the RTX 3090 in the 3DMark Time Spy Extreme benchmark.

NVIDIA GeForce RTX 4090 Almost Twice As Fast As RTX 3090 in 3DMark Time Spy Extreme Benchmark, Reportedly Hits 3 GHz Clocks With Ease

The NVIDIA GeForce RTX 4090 graphics card is going to be the green team’s flagship offering for 2022. There have been various leaks and rumors around the card throughout the year but from what we can tell, the launch is more or less expected around Q4 2022. With 3-4 months left in its launch, now the rumors are shifting the focus from specifications to performance numbers.

RTX 4090, TSE >19000

— kopite7kimi (@kopite7kimi) July 18, 2022

yes

— kopite7kimi (@kopite7kimi) July 18, 2022

Kopite7kimi was the first to report that the NVIDIA AD102 GPUs would be the first graphics chips to hit 100 TFLOPs of compute horsepower. Now the same leaker has shared the performance data in 3DMark Time Spy Extreme. According to the leaker, the NVIDIA GeForce RTX 4090 will deliver a total graphics score of over 19,000 points in the Time Spy Extreme benchmark.

If we compare it to existing cards, this score would put the NVIDIA GeForce RTX 4090 at least 90% faster than the RTX 3090 and 70% faster than the RTX 3090 Ti. This is indeed a massive jump but we have to remember that we are talking about a purely synthetic workload here. Gaming on the graphics card might be a whole different story and we don’t know whether this score is based on final clocks/optimizations or not. The leaker also states that for NVIDIA, it will be very easy to hit a clock speed of over 3 GHz which aligns with previous reports of TSMC’s 4N process node giving a huge boost to clock frequencies on Ada Lovelace GPUs.

So does NVIDIA, also easy.

— kopite7kimi (@kopite7kimi) July 18, 2022

19000 is a conservative score, so I wrote “>19000”. 💪

— kopite7kimi (@kopite7kimi) July 18, 2022

 

NVIDIA GeForce RTX 4090 ‘Rumored’ Specifications

The NVIDIA GeForce RTX RTX 4090 graphics card is expected to be powered by the top AD102-300 GPU but it is only the ‘Ti’ variant that will feature the full chip. The GeForce RTX 4090 will utilize a slightly cut-down configuration.

The NVIDIA GeForce RTX 4090 will use 128 SMs of the 144 SMs for a total of 16,384 CUDA cores. The GPU will come packed with 96 MB of L2 cache and a total of 384 ROPs which is simply insane. The clock speeds are not confirmed yet but considering that the TSMC 4N process is being used, we are expecting clocks to hit or even exceed the 3.0 GHz range. The core count is a 56% increase over the RTX 3090 so a lot of things such as clocks, cache, architecture and various other technologies are pushing the performance up by such a huge margin.

As for memory specs, the GeForce RTX 4090 is expected to rock 24 GB GDDR6X capacities that will be clocked at 21 Gbps speeds across a 384-bit bus interface. This will provide up to 1 TB/s of bandwidth. This is the same bandwidth as the existing RTX 3090 Ti graphics card and as far as the power consumption is concerned, the TBP is said to be rated at 450W which means that TGP may end up lower than that. The card will be powered by a single 16-pin connector which delivers up to 600W of power. It is likely that we may get 500W+ custom designs as we saw with the RTX 3090 Ti.

The graphics card is expected to launch in October 2022 and will be followed by the rest of the Ada Lovelace GPU-powered lineup of graphics cards.

NVIDIA GeForce RTX 4090 Ti & RTX 4090 ‘Preliminary’ Specs:

Graphics Card Name	NVIDIA GeForce RTX 4090 Ti	NVIDIA GeForce RTX 4090	NVIDIA GeForce RTX 3090 Ti	NVIDIA GeForce RTX 3090
GPU Name	Ada Lovelace AD102-350?	Ada Lovelace AD102-300?	Ampere GA102-350	Ampere GA102-300
Process Node	TSMC 4N	TSMC 4N	Samsung 8nm	Samsung 8nm
Die Size	~600mm2	~600mm2	628.4mm2	628.4mm2
Transistors	TBD	TBD	28 Billion	28 Billion
CUDA Cores	18432	16128	10752	10496
TMUs / ROPs	TBD / 384	TBD / 384	336 / 112	328 / 112
Tensor / RT Cores	TBD / TBD	TBD / TBD	336 / 84	328 / 82
Base Clock	TBD	TBD	1560 MHz	1400 MHz
Boost Clock	~2800 MHz	~2600 MHz	1860 MHz	1700 MHz
FP32 Compute	~103 TFLOPs	~90 TFLOPs	40 TFLOPs	36 TFLOPs
RT TFLOPs	TBD	TBD	74 TFLOPs	69 TFLOPs
Tensor-TOPs	TBD	TBD	320 TOPs	285 TOPs
Memory Capacity	24 GB GDDR6X	24 GB GDDR6X	24 GB GDDR6X	24 GB GDDR6X
Memory Bus	384-bit	384-bit	384-bit	384-bit
Memory Speed	24.0 Gbps	21.0 Gbps	21.0 Gbps	19.5 Gbps
Bandwidth	1152 GB/s	1008 GB/s	1008 GB/s	936 Gbps
TGP	600W	450W	450W	350W
Price (MSRP / FE)	$1999 US?	$1499 US?	$1999 US	$1499 US
Launch (Availability)	2023?	October 2022?	29th March 2022	24th September 2020

-->