NVIDIA's GeForce RTX 5060 Ti is a consumer graphics card in the GeForce RTX 50 Series, which is based on NVIDIA's Blackwell architecture. While this GPU brings only a modest increase in performance over the previous RTX 4060 Ti, and is about 40% slower than the next step up (RTX 5070), it does include many of the same major feature upgrades the RTX 50 Series is known for. There are improved video encoding and decoding capabilities, with added support for 4:2:2 chroma subsampling, as well as new generations of CUDA, tensor, and ray tracing cores. This card also benefits from the same brand-new, high-speed GDDR7 memory as the higher-end 50 Series models - though it is equipped with only 8GB, making this a more affordable and widely available option than the 5060 Ti models that have 16GB.
Most variants of the GeForce RTX 5060 Ti use a dual- or triple-fan cooling layout, with card sizes varying from 2- to 3-slot. Some models are compact enough to fit in small form factor cases, while others require a tower chassis.
Finally, in regards to connectivity, there are one HDMI 2.1 and three DisplayPort 2.1 plugs supporting a total of up to four displays at a maximum resolution of 7680x4320 (8K).
Most variants of the GeForce RTX 5060 Ti use a dual- or triple-fan cooling layout, with card sizes varying from 2- to 3-slot. Some models are compact enough to fit in small form factor cases, while others require a tower chassis.
Finally, in regards to connectivity, there are one HDMI 2.1 and three DisplayPort 2.1 plugs supporting a total of up to four displays at a maximum resolution of 7680x4320 (8K).
Specifications
| Chipset Manufacturer | NVIDIA |
| Product Line | GeForce |
| Series | RTX 50 Series |
| Model | 5060 Ti |
| Interface | PCI Express 5.0 x8 |
| Maximum Digital Resolution | 7680x4320 |
| Maximum Monitors Supported | 4 |
| TGP | 180 W |
GPU Specifications | |
| Core Speed | 2407 MHz |
| Boost Speed | 2572 Mhz |
| CUDA Cores | 4608 |
| AI Cores | 144 |
| RT Cores | 36 |
Memory Specifications | |
| Video Memory | 8GB |
| Memory Type | GDDR7 |
| Memory Speed | 1750 MHz |
| Memory Bus Width | 128-bit |
| Bandwidth | 448 GB/s |
Performance | |
| Double Precision Floating Point (Peak) | 0.3704 Tflops |
| Single Precision Floating Point (Peak) | 23.70 Tflops |
| Half Precision Floating Point (Peak) | 23.70 Tflops |
Additional Information | |
| DirectX Support | DirectX 12 |
| CUDA Support | 12.0 |
| OpenGL Support | 4.6 |
| Quadro Sync Support | No |