Key Differences
Advantages of GeForce RTX 4060
Advantages of GeForce RTX 5070 Ti
Specifications
Performance
| TGP | 115 W | 300 W |
Storage Details
| Bus | 128-bit | 256-bit |
Ports
| DisplayPort | 1.4a | 2.1b |
Other
| Forza Horizon 5 | 128796647 | 233165154123 |
| The Witcher 3 | 1401158444 | 23820814979 |
| Counter-Strike 2 | 21215311459 | 29922716883 |
| Far Cry 6 | 108957641 | 18016214588 |
| Hogwarts Legacy | 80635024 | 16313410860 |
| CoD: Modern Warfare III | 96906342 | 214206164115 |
| Ghost of Tsushima | 74584626 | 15012410868 |
| Cyberpunk 2077 | 85744320 | 19117012156 |
| Shadow of the Tomb Raider | 1291198446 | 283268201107 |
| 1080p High | 117 | 217 |
| 1080p Ultra | 94 | 185 |
| 1440p Ultra | 70 | 146 |
| 4K Ultra | 39 | 87 |
| Margin of Error | Low | Low |
| Time Spy | 10621 | 27784 |
| Solar Bay | 49195 | 136303 |
| Port Royal | 6053 | 19439 |
| Fire Strike | 28556 | 67197 |
| Wild Life Extreme | 20606 | 57631 |
| Night Raid | 121691 | 190729 |
| Background Blur | 186.9 img/sec | 297.9 img/sec |
| Face Detection | 112.7 img/sec | 218.6 img/sec |
| Horizon Detection | 3.92 Gpixels/sec | 10.1 Gpixels/sec |
| Edge Detection | 5.16 Gpixels/sec | 13.9 Gpixels/sec |
| Gaussian Blur | 4.94 Gpixels/sec | 14.8 Gpixels/sec |
| Feature Matching | 1.34 Gpixels/sec | 2.03 Gpixels/sec |
| Stereo Matching | 446.2 Gpixels/sec | 1290 Gpixels/sec |
| Particle Physics | 14935.1 FPS | 35438.3 FPS |
| API | OpenGL | OpenGL |
| G2D Mark | 1041 | 1342 |
| DirectX 11 | 174 FPS | 303 FPS |
| DirectX 12 | 76 FPS | 126 FPS |
| GPU Compute | 9206 Ops/s | 18821 Ops/s |
| Aztec Ruins Normal Tier | 709 FPS | 1450 FPS |
| Car Chase | 615.4 FPS | 1281.4 FPS |
| Manhattan 3.1.1 (1440p) | 496.1 FPS | 983.7 FPS |
| T-Rex | 2635.8 FPS | 4055.8 FPS |
| Tessellation | 3372.6 FPS | 10135.4 FPS |
| ALU 2 | 3284 FPS | 9247 FPS |
| Driver Overhead 2 | 280.8 FPS | 251.7 FPS |
| OS | Windows | Windows |
| Image Classification (SP) | 7696 | 14913 |
| Image Segmentation (HP) | 13706 | 45199 |
| Image Super Resolution (Q) | 23289 | 39360 |
| Face Detection (HP) | 31126 | 84188 |
| Pose Estimation (Q) | 78361 | 161400 |
| Text Classification (SP) | 3315 | 4010 |
| Machine Translation (HP) | 3491 | 7973 |
| Object Detection (SP) | 9386 | 18934 |
| Depth Estimation (Q) | 36778 | 67761 |
| Style Transfer (SP) | 148120 | 335879 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | May 18, 2023 | January 7, 2025 |
| Launch price (MSRP) | $299 | $749 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ada Lovelace | Blackwell 2.0 |
| GPU Codename | AD107 | GB203-200-A1 |
| Rival Equivalent | Radeon RX 7700 XT | Radeon RX 9070 XT |
| Base Clock | 1830 MHz | 2295 MHz |
| Boost Clock | 2460 MHz | 2452 MHz |
| Shading Units | 3072 | 8960 |
| Texture Mapping Units (TMUs) | 96 | 280 |
| Render Output Units (ROPs) | 48 | 96 |
| Compute Units (Pipelines) | 24 | 70 |
| Tensor Cores | 96 | 280 |
| Ray-tracing Cores | 24 | 70 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 24MB shared | 48MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
| Pixel Fill Rate | 118 GPixel/s | 235 GPixel/s |
| Texture Fill Rate | 236 GTexel/s | 687 GTexel/s |
| Interface | PCIe 4.0 x8 | PCIe 5.0 x16 |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 4 nm |
| Die Size | 159 mm² | 378 mm² |
| Transistor Count | 18 billion | 45.6 billion |
| Transistor Density | 113.21 MTr/mm² | 120.63 MTr/mm² |
| Max. Temperature | - | - |
| Memory Type | GDDR6 | GDDR7 |
| Memory Size | 8 GB | 16 GB |
| Memory Clock | - | 1750 MHz |
| Effective Memory Speed | - | 28000 Mbps |
| ECC | No | No |
| DirectX | 12 | 12.2 |
| Vulkan | 1.3 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 8.9 | 12.0 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 4 |