Nvidia made the RTX 4090 official at its special GeForce Beyond event today, after months of rumors and leaks detailing everything about the card. It looks like the fastest graphics card ever made, and according to Nvidia, it is. But as we knew from extensive talks about water coolers, it costs 450W of power.
Despite the RTX 4090 leading the lineup, Nvidia announced three new graphics cards. The RTX 4090 will be released on October 12th and the RTX 4080 will be released in November. All of them feature the new Ada Lovelace architecture as well as a significant increase in cores, clock speeds and performance compared to the previous generation.
| RTX4090 | RTX4080 16GB | RTX4080 12GB | |
| CUDA cores | 16,384 | 9,728 | 7,680 |
| memory | 24GB GDDR6X | 16GB GDDR6X | 12GB GDDR6X |
| Increase clock speed | 2520MHz | 2505MHz | 2610MHz |
| bus width | 384-bit | 256-bit | 192-bit |
| perfomance | 450W | 320W | 285W |
The improved specs are impressive even by last-gen standards. We’re seeing a 56% increase in core count as well as 76% more ray tracing and tensor cores on the RTX 4090 compared to the previous generation. The card features the same 24GB of GDDR6X memory, but Nvidia has boosted the GPU’s overall clock speed by 49%. And it’s important to remember that all of these improvements result from the new manufacturing process and architecture.
While there’s a lot new under the hood, there’s not much new on the outside. Nvidia sticks to the Founder’s Edition design it had in the previous generation without an updated font for branding. The fans also look different, with smaller blades and a more aggressive tilt.
According to Nvidia, the RTX 4090 can outperform the RTX 3090 Ti by 2x to 4x due to the new Ada Lovelace architecture and some key performance improvements. One of these is Shader Execution Reordering (SER), which reorders ray tracing to boost performance. However, Nvidia hasn’t provided any concrete benchmarks, so we’ll have to wait for third-party tests.
These improvements also apply to the two versions of the RTX 4080, with Nvidia citing the same 2x to 4x improvement over the RTX 3080 Ti.
In addition to the new architecture, the cards feature third-generation ray tracing cores and fourth-generation tensor cores. These support SER and Nvidia’s third version of Deep Learning Super Sampling (DLSS). Nvidia showed a demo of Microsoft flight simulator Runs on DLSS 3 and achieves well over 100 fps.
However, improvements come at the expense of performance and price. The RTX 4090 has a peak power of 450 watts, which is the same as the RTX 3090 Ti. It also costs $1,600, which is $100 more than the RTX 3090 at launch. The 16GB RTX 4080 costs $1,200, while the 12GB RTX 4080 costs $900, which is a huge premium over the RTX 3080’s introductory price of $700.
It’s a big price increase that will certainly turn some potential buyers away, but we’ll have to wait for third-party testing to see if the increase is worth it. After all, AMD announced today that it will launch its next-gen GPUs on November 7th, so the GPU market is about to heat up.
Editor’s Recommendations