NVIDIA is readying the new GeForce RTX 5090 SE graphics card, according to a report by GameGPU. This SKU could fill the gap between the current RTX 5080 and the flagship RTX 5090. Unlike the RTX 5090D and RTX 5090D V2, the RTX 5090 SE isn't a region-specific SKU aimed at complying with U.S. AI accelerator export controls, but is rather a mainline gaming GPU product. It is based on the same "GB202" silicon as the RTX 5090, but is cut down from it, featuring fewer streaming multiprocessors (SM), and a narrower 384-bit wide GDDR7 memory interface. The memory size is still 32 GB, achieved using a mixed density of 24 Gb and 16 Gb memory chips.
NVIDIA is carving the RTX 5090 SE out of the "GB202" by enabling 110 out of the 192 SM physically present on the silicon, resulting in 14,080 CUDA cores, 110 RT cores, 440 Tensor cores, 440 TMUs, and an unknown ROP count, probably 144. Meanwhile, the TGP of the RTX 5090 SE is expected to be around 500 W, down from 575 W of the RTX 5090. NVIDIA is looking to target a launch MSRP of $1,500, but you can be sure that the street price will be much higher.