Nvidia has officially unveiled its next-generation GeForce RTX 50-series GPUs at CES 2025, introducing the RTX 5090 and RTX 5080 models. These GPUs promise significant performance enhancements for gaming and professional applications.
Nvidia GeForce RTX 5090 and RTX 5080: Key Specifications
RTX 5090
- CUDA Cores: 21,760
- Memory: 32GB GDDR7
- Memory Bandwidth: 1,792 GB/s
- Total Graphics Power (TGP): 575W
- Recommended Power Supply: 1000W
- Price: $1,999
- Availability: January 30, 2025
RTX 5080
- CUDA Cores: 10,752
- Memory: 16GB GDDR7
- Memory Bandwidth: 960 GB/s
- Total Graphics Power (TGP): 360W
- Recommended Power Supply: 850W
- Price: $999
- Availability: January 30, 2025
Performance Enhancements
Nvidia claims the RTX 5090 delivers up to twice the performance of the RTX 4090, largely due to advancements in DLSS 4 technology and the new Blackwell architecture. In demonstrations, the RTX 5090 achieved 238 frames per second in “Cyberpunk 2077” with full ray tracing and DLSS 4 enabled, compared to 106 frames per second on the RTX 4090 with DLSS 3.5.
Design and Compatibility
The RTX 5090 Founders Edition features a redesigned cooling system with two double flow-through fans and a 3D vapor chamber. Notably, it occupies only two slots, making it suitable for small form factor PCs—a significant change from the larger RTX 4090.
Additional Models
Alongside the flagship models, Nvidia announced the RTX 5070 Ti and RTX 5070, priced at $749 and $549 respectively, with availability expected in February. The RTX 5070 is particularly noteworthy, as Nvidia suggests it offers performance comparable to the RTX 4090, attributed to DLSS 4 improvements.
