Key Differences
Advantages of GeForce RTX 5070
Advantages of GeForce RTX 5060 Ti (16GB)
Specifications
Performance
| TGP | 250 W | 180 W |
Storage Details
| Bus | 192-bit | 128-bit |
Ports
| DisplayPort | 2.1b | 2.1b |
Other
| Forza Horizon 5 | 19213713097 | 1591049570 |
| The Witcher 3 | 20918513372 | 18415510860 |
| Counter-Strike 2 | 28221115683 | 26520214480 |
| Far Cry 6 | 16214613278 | 14112511067 |
| Hogwarts Legacy | 1401139051 | 110927238 |
| CoD: Modern Warfare III | 18317313789 | 1391329965 |
| Ghost of Tsushima | 1241078955 | 100846738 |
| Cyberpunk 2077 | 1641439745 | 1181046933 |
| Shadow of the Tomb Raider | 257243186101 | 19117413471 |
| 1080p High | 190 | 156 |
| 1080p Ultra | 162 | 130 |
| 1440p Ultra | 128 | 100 |
| 4K Ultra | 75 | 58 |
| Margin of Error | Low | Low |
| Time Spy | 22660 | 16030 |
| Solar Bay | 106084 | 75543 |
| Port Royal | 14316 | 10142 |
| Fire Strike | 58020 | 42459 |
| Wild Life Extreme | 43610 | 30109 |
| Night Raid | 177582 | 151273 |
| Background Blur | 254.4 img/sec | 243.1 img/sec |
| Face Detection | 180.6 img/sec | 149.5 img/sec |
| Horizon Detection | 7.91 Gpixels/sec | 5.35 Gpixels/sec |
| Edge Detection | 10.2 Gpixels/sec | 6.88 Gpixels/sec |
| Gaussian Blur | 10.7 Gpixels/sec | 7.76 Gpixels/sec |
| Feature Matching | 1.84 Gpixels/sec | 1.57 Gpixels/sec |
| Stereo Matching | 975.7 Gpixels/sec | 740.2 Gpixels/sec |
| Particle Physics | 27816.5 FPS | 22183.7 FPS |
| API | OpenGL | OpenGL |
| G2D Mark | 1310 | 1227 |
| DirectX 11 | 279 FPS | 218 FPS |
| DirectX 12 | 106 FPS | 90 FPS |
| GPU Compute | 14892 Ops/s | 11549 Ops/s |
| Aztec Ruins Normal Tier | 1199.4 FPS | 903.4 FPS |
| Car Chase | 995.8 FPS | 792.7 FPS |
| Manhattan 3.1.1 (1440p) | 859 FPS | 641 FPS |
| T-Rex | 4075 FPS | 2827.5 FPS |
| Tessellation | 6657.7 FPS | 5095.6 FPS |
| ALU 2 | 5998.5 FPS | 4413.6 FPS |
| Driver Overhead 2 | 276.3 FPS | 265.7 FPS |
| OS | Windows | Windows |
| Image Classification (SP) | 12270 | 10281 |
| Image Segmentation (HP) | 30237 | 29909 |
| Image Super Resolution (Q) | 35585 | 26549 |
| Face Detection (HP) | 62662 | 59010 |
| Pose Estimation (Q) | 145190 | 117200 |
| Text Classification (SP) | 4198 | 3993 |
| Machine Translation (HP) | 6233 | 6647 |
| Object Detection (SP) | 16709 | 12742 |
| Depth Estimation (Q) | 58300 | 44856 |
| Style Transfer (SP) | 246598 | 175892 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 7, 2025 | April 15, 2025 |
| Launch price (MSRP) | $549 | $429 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Blackwell 2.0 | Blackwell 2.0 |
| GPU Codename | GB205-300 | GB206-300 |
| Rival Equivalent | Radeon RX 9070 | - |
| Base Clock | 2160 MHz | 2407 MHz |
| Boost Clock | 2512 MHz | 2572 MHz |
| Shading Units | 6144 | 4608 |
| Texture Mapping Units (TMUs) | 192 | 144 |
| Render Output Units (ROPs) | 80 | 48 |
| Compute Units (Pipelines) | 48 | 36 |
| Tensor Cores | 192 | 144 |
| Ray-tracing Cores | 48 | 36 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 48MB shared | 32MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
| Pixel Fill Rate | 201 GPixel/s | 123 GPixel/s |
| Texture Fill Rate | 482 GTexel/s | 370 GTexel/s |
| Interface | PCIe 5.0 x16 | PCIe 5.0 x8 |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 5 nm |
| Die Size | 263 mm² | 181 mm² |
| Transistor Count | 31.1 billion | 21.9 billion |
| Transistor Density | 118.25 MTr/mm² | 120.99 MTr/mm² |
| Memory Type | GDDR7 | GDDR7 |
| Memory Size | 12 GB | 16 GB |
| Memory Clock | 1750 MHz | 1750 MHz |
| Effective Memory Speed | 28000 Mbps | 28000 Mbps |
| ECC | No | No |
| DirectX | 12.2 | 12.2 |
| Vulkan | 1.4 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 12.0 | 12.0 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 4 | DLSS 4 |
| Max. Temperature | - | 87°C |