NVIDIA’s GeForce RTX 40-series graphics cards are getting closer and closer to their launch but still don’t have many performance benchmarks on them. This is because, to prevent leaks, NVIDIA restricts pre-launch drivers from being available to the general public.
However, a leaker, @kopite7kimi, has tweeted that the flagship RTX 4090 will have >19000 graphics score on 3DMark’s TimeSpy Extreme.
To provide some perspective, the current gen flagship RTX 3090 Ti has a graphics score of 11400 on the same test. This is a whopping 66% difference between the two scores.
RTX 3090 has a score of 10440 on 3DMark TimeSpy Extreme. This makes RTX 4090 82% faster than its predecessor.
Not only this, no card ever has crossed the 15000 mark as the current world record of the 3DMark TimeSpy Extreme benchmark is from user “biso biso,” with an LN2 cooled EVGA RTX 3090 Ti Kingpin Edition graphics card punching out a world recorded graphics result of 14,611 points.
So, the Ada Lovelace card is 30% faster than the current world record. We did know that NVIDIA is going all out with its GPU lineup this time, but according to these results, it might be the biggest performance jump we have ever seen from NVIDIA.
The RTX 4090 is rumored to feature 16384 CUDA Cores, 52% more than RTX 3090 Ti. That would mean that the core count increase is just one variable that makes the next flagship even faster. This may be due to higher clocks or higher TDP, both expected to increase for the next generation.
Power consumption is one aspect that has increased to ~450W, which will require considerable cooling as well to negate the heating effects of such a performance beast of a GPU.
The RTX 4090 will use AD102 GPU. The base and boost clocks for the processor measure 2235 MHz and 2520 MHz, while the actual in-game clock goes up to 2750 MHz.
In comparison, there is a 60% and 49% increase in the base clock and the boost clock to the RTX 3090, its RTX 30 ‘Ampere’ series counterpart SKU.
We don’t know if the leak can be trusted or not, so without more information, we shouldn’t set these scores to stone. NVIDIA’s next-gen RTX 40 series graphics cards are set for a Q4 2022 launch.
NVIDIA Corporation is an American multinational technology company incorporated in Delaware, based in Santa Clara, California. They design graphics processing units (GPUs) for the gaming and professional markets, as well as system on chip units (SoCs) for the mobile computing and automotive market.
Best known for the “GeForce” lines of GPUs, they are a direct competitor to AMD’s “Radeon” series. NVIDIA has also expanded its offerings with its handheld game consoles Shield Portable, Shield Tablet, and Shield Android TV and its cloud gaming service GeForce Now.