More rumblings and rumors surrounding Nvidia GeForce RTX 5090 specs have recently come to light, painting the graphics card as a substantial markup versus the best Nvidia currently has to offer. In fact, the alleged improvements leave the would-be flagship ahead of the RTX 4090 by as much as 70%.
While the Nvidia GeForce RTX 5090 release date isn’t expected to arrive for a while yet, this hasn’t stopped potential nuggets of information on its design from escaping team green’s headquarters. These leaks may also give us some indication of how powerful the GeForce RTX 5000 series will be as a whole.
| Rumored Nvidia GeForce RTX 5090 specs | |
| GPU die | GB202 |
| CUDA cores | 24,576 |
| Tensor cores | TBC |
| RT cores | TBC |
| Base clock | TBC |
| Boost clock | 2.90GHz (2,898MHz) |
| VRAM | TBC |
| Memory clock | TBC |
| Memory bus width | 512-bit |
| Memory Bandwidth | 1.5TB/s (1,532GB/s) |
| L2 Cache | 128MB |
| TDP | TBC |
According to Chiphell user and reliable Nvidia leaker panzerlied, “the scale [of the RTX 5090] is increased by 50%, the memory bandwidth is increased by 52%, the cache is increased by 78%, and there is a 15% frequency increase and a 1.7X improvement.” They clarified in a later post that “this is for comparison with [the Nvidia GeForce RTX 4090], not for comparison with AD102.”
While these changes are somewhat cryptic, our presumptions for what ‘scale’, ‘cache’, ‘frequency’, and ‘improvement’ line up with Videocardz‘s assessment. Suffice to say, if these specs hold water, the RTX 5090 is shaping up to be a more than worthy successor to the RTX 4090.
In the here and now, however, the Nvidia GeForce RTX 4070 finally has a worthy opponent in the form of the AMD Radeon RX 7800 XT. Check out our reviews for both GPUs to see which one is right for you.