Nvidia GeForce RTX 4070 vs Nvidia GeForce RTX 2080 Ti
55
out 100
VS
51
out 100
Compared 2 processors: Nvidia GeForce RTX 4070, vs Nvidia GeForce RTX 2080 Ti. Below are specs, tests, pros and cons for each device
Review
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
Tests & specs
Specs & test comparisonGames
| Game title | 1080p (High) 1080p (Ultra) 1440p (Ultra) 4K (Ultra) | |
 Forza Horizon 5 | 170 113 105 79 | 152 98 87 65 |
 The Witcher 3 | 191 160 114 61 | 172 140 103 55 |
 Counter-Strike 2 | 262 207 148 82 | 253 199 137 80 |
 Far Cry 6 | 148 135 112 71 | 133 122 98 59 |
 Hogwarts Legacy | 120 96 78 43 | 101 83 64 34 |
 COD Modern Warfare 3 | 154 141 110 72 | 126 117 88 56 |
 Ghost of Tsushima | 104 87 74 40 | 93 75 61 34 |
 Cyberpunk 2077 | 133 115 78 34 | 109 95 63 27 |
 Shadow of the Tomb Raider | 209 194 148 81 | 174 156 116 63 |
| 1080p High | 166 | 146 |
| 1080p Ultra | 139 | 121 |
| 1440p Ultra | 107 | 91 |
| 4K Ultra | 63 | 53 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 17825 | 14660 |
| Solar Bay | 82645 | 64266 |
| Port Royal | 11149 | 9109 |
| Fire Strike | 44109 | 35668 |
| Night Raid | 152587 | 114857 |
| Background Blur | 233 frames/s | 211 frames/s |
| Face Detection | 141.7 frames/s | 141.3 frames/s |
| Horizon Detection | 6.62 Gpix/sec | 6.24 Gpix/sec |
| Edge Detection | 9.19 Gpix/sec | 8.1 Gpix/sec |
| Gaussian Blur | 9.2 Gpix/sec | 9.22 Gpix/sec |
| Feature Matching | 1.78 Gpix/sec | 1.46 Gpix/sec |
| Stereo Matching | 845.4 Gpix/sec | 627.3 Gpix/sec |
| Particle Physics | 25043.9 fps | 16980.5 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 1165 | 928 |
| DirectX 11 | 245 fps | 190 fps |
| DirectX 12 | 102 fps | 84 fps |
| GPU Compute | 14820 Ops/s | 10244 Ops/s |
| Aztec Ruins (Normal) | 1039 fps | 776.4 fps |
| Car Chase | 900 fps | 675.9 fps |
| Manhattan 3.1.1 (1440p) | 761.2 fps | 655.7 fps |
| T-Rex | 3848.1 fps | 3193.1 fps |
| ALU 2 | 5980.8 fps | 4775.9 fps |
| Driver Overhead 2 | 296.7 fps | 278.9 fps |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
| Tessellation | 6200.7 | 4776.1 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Announced | April, 13, 2023 | September, 27, 2018 |
| Form Factor | PC use | PC use |
| Use case | Gaming | Gaming |
| Segment | Mid-range | High-end |
| Architecture | Ada Lovelace | Turing |
| Codename | AD104 | TU102 |
| Price | 599 | 999 |
GPU
| GPU Frequency | 1920 MHz | 1350 MHz |
| Boost GPU Frequency | 2475 MHz | 1545 MHz |
| Shader Units | 5888 | 4352 |
| TMUs | 184 | 272 |
| ROPs | 64 | 88 |
| Execution Units | 46 | 68 |
| Ray Tracing Cores | 46 | 68 |
| Tensor Cores | 184 | 544 |
| L1 cache | 128 KB/core | 64 KB/core |
| L2 cache | 36000 KB/core | 5632 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 158 Gpix/sec | 136 Gpix/sec |
| Texture Fill Rate | 455 GTex/s | 420 GTex/s |
| FLOPS | 29.1 TFLOPS | 13.4 TFLOPS |
Process
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| TGP | 200 W | 250 W |
| Process | TSMC | TSMC |
| Process tech. | 5 nm | 12 nm |
| Transistor Size | 294 mm² | 754 mm² |
| Transistor count | 35 billion | 18 billion |
| Transistor density | 119.05 MTr/mm² | 23.87 MTr/mm² |
Memory
| Interface | GDDR6X | GDDR6 |
| Memory Frequency | 1313 MHz | 1750 MHz |
| Bus | 192 bit | 352 bit |
| ECC support | No | No |
| Effective Memory Speed | 21000 MB/s | 14000 MB/s |
| Memory Size | 12 GB | 11 GB |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| CUDA | 8.9 | 7.5 |
| DisplayPort | 1.4a | 1.4a |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 2 |
Results
No clear favorite identified yet; updates may follow as new data arrives.
Survey
Total Votes: 0
