NVIDIA's next-generation GeForce RTX 50 series "Blackwell" GPU configurations have been leaked: we now have the skinny on the GB202, GB203, GB205, GB206, and GB207 GPUs.
In a new post on X by leaker "kopite7kimi" we're learning that the flagship GB202 GPU -- the one that will power the GeForce RTX 5090 flagship graphics card -- will reportedly have a massive 512-bit memory bus, powered by ultra-fast, next-generation GDDR7 memory. GB202 will reportedly have 24,576 CUDA cores, which is a 33% increase of CUDA cores inside of AD102, the GPU that powers the RTX 4090.
GB202 will reportedly have a total of 12 SMs, each with 8 TPCs for a total of 96 TPCs and each TPC features 2 SMs for a total of 192 SMs. GB202 will support a massive 512-bit memory bus, but it can be sliced up into different configurations depending on the SKU: like the recent rumors of a 448-bit memory bus, but also down into 384-bit, 320-bit, and other designs.
GB203 will most likely power the GeForce RTX 5080, with 7 GPCs, each with 6 TPCs for a total of 42 TPCs that end up with 84 SMs in total. GB203 will reportedly have a smaller 256-bit memory bus, but we can expect some wicked performance from the GeForce RTX 5080 thanks to not just its next-gen Blackwell GPU, but also next-gen GDDR7 memory.
- Read more: NVIDIA's next-gen GeForce RTX 5090 features 'physically monolithic' GB202 GPU die
- Read more: NVIDIA GeForce RTX 5090 rumor: 16 next-gen GDDR7 memory modules, 32GB GDDR7
- Read more: NVIDIA GeForce RTX 5090 Founders Edition PCB reportedly split into three parts
GB205 should power the new GeForce RTX 5070 and GeForce RTX 5070 Ti graphics cards, with 5 GPCs, each with 5 TPCs for a total of 25 TPCs and 50 SMs in total, we should expect a 192-bit memory bus on GB205.
GB206 will be the mainstream Blackwell GPU, with 3 GPCs and 6 TPCs per GPC with 18 TPCs in total, we should expect 36 SMs and a 128-bit memory bus.
GB207 is the last GPU, but instead of only using next-gen GDDR7 memory, GB207 will be an entry-level GeForce RTX 50 series GPU (think RTX 5060, RTX 5050) and will retain the current-gen GDDR6 memory standard. We can expect 2 GPCs with 5 TPCs each for a total of 10 TPCs and 20 SMs. There's reportedly going to be options of GDDR7 and GDDR6, but we'll wait and see.
GDDR7 details: Samsung has its next-gen GDDR7 memory ready for NVIDIA, with GDDR7 memory speeds of 28Gbps and 32Gbps. We could see the faster 32Gbps GDDR7 on the RTX 5090 and 28Gbps GDDR7 on the RTX 5080, and probably on the rest of the RTX 50 series GPU fleet.
- Read more: NVIDIA GeForce RTX 5090 and RTX 5080 will be available within a few weeks of each other
- Read more: NVIDIA testing 250W to 600W coolers for next-gen GeForce RTX 50 series GPUs
- Read more: NVIDIA's next-gen GeForce RTX 5080 rumored to now launch BEFORE the RTX 5090
- Read more: NVIDIA's next-gen RTX 5090, RTX 5080 Laptop GPUs rumored with 16GB VRAM
- Read more: NVIDIA rumored to ONLY launch GeForce RTX 5090 this year
- Read more: NVIDIA's next-gen GeForce RTX 5090, RTX 5080 rumored for Computex 2024 reveal
- Read more: NVIDIA to unveil top-end GeForce RTX 5090, and high-end RTX 5080 at first later this year
4K performance: NVIDIA's next-generation ultimate gaming GPU in the GeForce RTX 5090 should have 50-70% more performance across the board compared to the RTX 4090, especially at the higher-end 4K resolution. 4K 120FPS gaming should be an even easier achievement for the RTX 5090 than it is for the RTX 4090. We've got 4K 240FPS coming this year and in 2025, so the RTX 5090 will be the GPU of choice for 4K 240FPS gaming in the future.
RT performance: This is where the biggest performance improvements of the next-gen Blackwell-based GeForce RTX 50 series GPUs will come: ray tracing. Expect some rather large 2-3x performance gains using RT, probably 4x or more in some cases with the RTX 5090 and RTX 5080 against their RTX 40 series counterparts. Throw new DLSS 4 on top, and you've got some wowzers RT performance.
DLSS 4: This is probably my personal favorite part of the excitement of next-gen GPUs from NVIDIA, AI-powered upscaling with a next-gen DLSS 4 that works only on the new Blackwell-based RTX 50 series GPUs. We should expect even higher image quality than offered by DLSS 3.x and new levels of performance with DLSS 4 enabled on a new RTX 5090 or RTX 5080 graphics card.
Power efficiency: NVIDIA's current-gen GeForce RTX 4090 can use anywhere between 450W and 600W of power depending on the model and overclocking, but the new GeForce RTX 50 series GPUs will offer far more performance-per-watt of the leading RTX 4090 and RTX 4080 SUPER graphics cards. Another exciting part to see unravel in the near future.