The upcoming Blackwell "GB203" GPU die has been leaked, the GPU that should power NVIDIA's next-gen GeForce RTX 5080 desktop graphics card, and the RTX 5090 Laptop GPU and RTX 5080 Laptop GPU. Check it out, in all its TSMC 4nm glory:

NVIDIA Blackwell GB203 die (source: Moore's Law is Dead)
In a new video, leaker Moore's Law is Dead has posted a purported GB203 die shot which will power the second-fastest Blackwell desktop gaming GPU -- the GeForce RTX 5080 -- and what will be the two best discrete GPUs inside of laptops in 2025: the GeForce RTX 5090 Laptop GPU and the GeForce RTX 5080 Laptop GPU. We'll also have next-generation GDDR7 memory across the board.
This is just a leak, so the GB203 GPU die that we're looking at might not be 100% making its way into the RTX 5080, or the RTX 5090 Laptop + RTX 5080 Laptop GPUs, it could very well make it into a laptop-focused Blackwell-based workstation GPU. We only have a couple of months to wait until we get some confirmation, probably weeks at this rate.
- Read more: NVIDIA GeForce RTX 5090, RTX 5080 later this year: RTX 5070 at CES 2025
- Read more: RTX 5080 leaked specs: 16GB GDDR7 at fastest 32Gbps, 1TB/sec bandwidth
- Read more: RTX 5080: launches with 16GB GDDR7, but 24GB GDDR7 model rumored
- Read more: RTX 5090 + RTX 5080: launch at CES 2025, single 12V-2x6 power, PCIe 5.0, DP 2.1a
- Read more: RTX 5080 leaked specs: 16GB GDDR7, over 10K CUDA cores, and 400W power
- Read more: RTX 50 pricing leak: 5090 for $1999-$2499, 5080 for $1199-$1499, 5070 for $599-$699
NVIDIA GeForce RTX 5080 details so far:
RTX 5080 16GB + RTX 5080 24GB: We've also heard rumors that NVIDIA will offer the RTX 5080 with 16GB GDDR7, but have a newer upgraded RTX 5080 with 24GB of GDDR7 memory leaving the RTX 5090 with its monster 32GB GDDR7 memory at the top.
16GB GDDR7 @ 32Gbps: We don't have more VRAM on the RTX 5080, with both the RTX 4080 and RTX 5080 having 16GB of VRAM. The big upgrade here is NVIDIA is using ultra-fast, next-gen GDDR7 memory... so, same 16GB, but radically faster (and cooler).
Up to 1.0TB/sec memory bandwidth: The RTX 4080 has 716GB/sec of memory bandwidth, so with somewhere between 896GB/sec and 1.0TB/sec of memory bandwidth from the RTX 4080 is going to offer huge performance improvements at 1440p and 4K.
400W of power: Not a big upgrade in power consumption on the RTX 5080 which is rumored with a 400W TDP, another 80W more than the RTX 4080 which had a 320W rated TDP (again, custom AIB models are on the market with higher power consumption, the same applies to the new RTX 5080 in the months ahead).
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.