NVIDIA GeForce RTX 4090 CUDA performance benchmark shows 60% improvement over RTX 3090 Ti

NVIDIA’s first unofficial GeForce RTX 4090 graphics card benchmark has been leaked at Geekbench 5 . Database before launching it.

NVIDIA GeForce RTX 4090 shows strong 60% CUDA performance over RTX 3090 Ti in Geekbench 5 benchmark

While NVIDIA is providing gamers with DLSS 3 and Ray Tracing performance numbers, there has been little information regarding the raster performance of their next-gen parts. Now, we have our first non-DLSS and non-RT benchmark leak inside the Geekbench 5 CUDA database.

The NVIDIA GeForce RTX 4090, without knowing if this is a Founders Edition reference or a custom AIB build, was tested on an AMD Ryzen 9 7950X CPU platform with 32GB of DDR5-6000 DRAM. The graphics card provided a maximum reported frequency of around 2.58 GHz. In terms of CUDA performance, the graphics card scored 417,713 points. For comparison, the RTX 3090 Ti scores a total of 260,346, while the RTX 3090 scores a total of 238,123 in the same benchmark. This is a 60% and 75% increase over those graphics cards, respectively.

The NVIDIA GeForce RTX 4090 delivers 60% higher performance than the RTX 3090 Ti, and 75% higher performance than the RTX 3090 in the Geekbench CUDA benchmark. (Image credits: Benchlife)

70722

141444

212166

282888

353610

424332

“Official” NVIDIA GeForce RTX 4090 Specifications – $1,599 Price

nvidia GeForce RTX 4090 It will use 128 SMs of the 144 SMs for a total of 16,384 CUDA cores. The GPU will come packed with 96MB of L2 cache and a total of 384 ROPs which is just insane but considering that the RTX 4090 is a reductive design, it might have slightly fewer L2 and ROP. Clock speeds are yet to be confirmed but considering that the TSMC 4N process is in use. Clock speeds are rated up to 2.6GHz and NVIDIA Claiming speeds over 3GHz with overclocking which you can read more about here.

See also  AMD RDNA 3 Navi 31 'GFX1100', Navi 32 'GFX1102', Navi 33 'GFX1101' Discrete Display Core Next 3.2 GPUs, APUs Get DCN 3.1.4

As for the memory specs, the GeForce RTX 4090 will feature 24GB GDDR6X capacities which will be clocked at 21Gbps via the 384-bit bus interface. This will save up to 1 TB/sec of bandwidth. That’s the same bandwidth as the current RTX 3090 Ti graphics card and as far as power consumption is concerned, the TBP is rated at 450W. The card will be powered by a single 16-pin connector that delivers up to 600 watts of power. Customized forms will present higher TBP goals.

NVIDIA GeForce RTX 4090 GPU Officially Launched On October 12, when NVIDIA builds and custom card partners become publicly available. Proshop does not take pre-orders, especially since many GPUs are available.

news source: Seating

Products mentioned in this post

Leave a Reply

Your email address will not be published.