Graphic Cards 

Built for What IT Heroes do. 

Nvidia GeForce RTX 3080

CUDA cores: 8,704 Base clock: 1,440MHz Boost clock: 1,710MHz TFLOPs: 29.76 Memory: 10GB GDDR6X Memory clock: 19GT/s Memory bandwidth: 760GB/s

AMD Radeon RX 6899 XT

RDNA cores: 4,608 Base clock: 1,825MHz Boost clock: 2,250MHz TFLOPs: 20.74 Memory: 16GB GDDR6 Memory clock: 16GT/s Memory bandwidth: 512GB/s

Nvidia GeForce RTX 3060 Ti

CUDA cores: 4,864 Base clock: 1,410MHz Boost clock: 1,665MHz TFLOPs: 16.20 Memory: 8GB GDDR6Memory clock: 14GT/s Memory bandwidth: 448GB/s

Nvidia GeForce 3070

CUDA cores: 5,888 Base clock: 1,500MHz Boost clock: 1,725MHz TFLOPs: 20.37 Memory: 8GB GDDR6 Memory clock: 14GT/s Memory bandwidth: 448GB/s

AMD Radeon RX 6900 XT

RDNA cores: 5,120 Base clock: 1,825MHz Boost clock: 2,250MHz TFLOPs: 23.04 Memory: 16GB GDDR6 Memory clock: 16GT/s Memory bandwidth: 512GB/s

Nvidia GeForce RTX 3080 Ti

CUDA cores: 10,240 Base clock: 1,365MHz Boost clock: 1,665MHz TFLOPs: 34.10 Memory: 12GB GDDR6X Memory clock: 19GT/s Memory bandwidth: 912.4GB/s

Nvidia GeForce RTX 3060

CUDA cores: 3,584 Base clock: 1,320MHz Boost clock: 1,777MHzTFLOPs: 12.74 Memory: 12GB GDDR6 Memory clock: 15GT/s Memory bandwidth: 360GB/s

Nvidia GeForce RTX 3050

CUDA cores: 2,560 Base clock: 1,552MHz Boost clock: 1,777MHz TFLOPs: 9.098 Memory: 8GB GDDR6 Memory clock: 14GT/s Memory bandwidth: 224GB/s


The older GTX prefix is now used to denote older Nvidia graphics cards which don't have the extra AI and ray tracing silicon that the RTX-level cards do. This RTX prefix was introduced three years ago with the RTX 20-series, and highlights which cards have GPUs which sport both the Tensor Cores and RT Cores necessary for real-time ray tracing and Deep Learning Super Sampling.