The $ 1,599 NVIDIA GeForce RTX 4090 will be available on October 12

After months of waiting and controversy among expansion card partners, NVIDIA’s 40-series GPUs are finally here. The company today unveiled the GeForce RTX 4090 and GeForce RTX 4080 at its GTC 2022 speech. Taking full advantage of its new “Ada Lovelace” architecture, NVIDIA says these two GPUs offer significantly improved ray tracing performance. The company worked with Taiwan Semiconductor Manufacturing Company (TSMC) to jointly develop a new “4N” manufacturing process, which NVIDIA says is up to two times more energy efficient than the 8nm process it used in its 30 series cards.

Ray tracing performance has been significantly improved with Ada Lovelace, which uses NVIDIA’s new third generation RT cores and a new rendering technique called Shader Execution Reordering and DLSS 3.0. In some games, NVIDIA said you can expect two to three times better ray tracing performance than what was possible with Ampere GPUs. Company presentation Cyberpunk 2077 runs at a near-constant 100fps with all in-game ray tracing set to max. NVIDIA says rasterization performance is up to two times faster thanks to the new architecture.


The first of the new NVIDIA Ada Lovelace GPUs will arrive next month when the GeForce RTX 4090 goes on sale for $ 1,599 on October 12. With 24GB of GDDR6X memory, NVIDIA says its latest flagship is two to four times faster than the 3090 Ti while consuming the same amount of power. Good because it starts at $ 100 more than its predecessor. Inside NVIDIA’s RTX 4090, it was possible to fit 16,384 CUDA cores with a base speed of 2.23 GHz.

In addition to the 4090 model, NVIDIA will offer two different variants of the RTX 4080. The base model, starting at $ 899, includes 12GB of GDDR6X memory, while the 16GB version will give you a nice $ 1,199. Both configurations will appear in November. However, NVIDIA will only sell the Founders Edition of the more expensive model. For the 12 GB version, you need to contact the company’s partners.

In terms of performance, the 16 GB 3080 has 9728 Cuda cores and a base clock of 2.21 GHz, with a maximum boost clock of 2.51 GHz. Meanwhile, the 12GB model has the more modest 7,680 CUDA cores, but a higher 2.31GHz base clock. Luckily, you probably won’t need to upgrade your PSU if you’re planning to upgrade from the 3070 or 3080, and NVIDIA recommends a 700 watt PSU for the 12GB variant and a 750 Watt PSU for the more powerful sibling. However, if you decide to buy a new PSU, you’ll want to wait for more ATX 3.0 PSUs to arrive later this year. That’s because at least the Founders Edition models will support the new 16-pin PCIe Gen-5 connector standard. That said, NVIDIA will also offer an 8-pin adapter for those who don’t want to rewire their system.

NVIDIA’s 40 series GPUs arrived at a difficult time for the company. During most of the pandemic, it was impossible to buy the latest GeForce GPUs at MSRP due to demand from both gamers and cryptocurrency miners. Everything has changed in recent months due to the recent cryptocurrency crash and the long-awaited transition of Ethereum to breaking evidence of the stake. As a result of these events, the used market was flooded with 30-series GPUs, making it practically impossible for AIB’s partners and resellers to sell new video cards at MSRP.

All products recommended by Engadget are selected by our editorial team, independent of our parent company. Some of our stories contain affiliate links. If you buy something through one of these links, we may receive an affiliate commission. All prices are correct at the time of publication.

Leave a Reply