Nvidia GeForce RTX 4070 Ti vs Nvidia GeForce RTX 3060 Ti
67
out 100
VS
41
out 100
Compared 2 processors: Nvidia GeForce RTX 4070 Ti, vs Nvidia GeForce RTX 3060 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 | 201 136 129 100 | 132 85 77 55 |
 The Witcher 3 | 220 189 136 70 | 152 123 91 47 |
 Counter-Strike 2 | 284 219 160 83 | 226 170 122 67 |
 Far Cry 6 | 159 149 130 83 | 114 104 81 47 |
 Hogwarts Legacy | 139 113 92 52 | 86 70 55 26 |
 COD Modern Warfare 3 | 182 177 135 92 | 109 99 69 45 |
 Ghost of Tsushima | 124 104 90 55 | 82 66 48 30 |
 Cyberpunk 2077 | 162 144 96 47 | 92 83 51 23 |
 Shadow of the Tomb Raider | 257 240 188 102 | 139 129 97 52 |
| 1080p High | 192 | 126 |
| 1080p Ultra | 163 | 103 |
| 1440p Ultra | 128 | 77 |
| 4K Ultra | 76 | 44 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 22766 | 11708 |
| Solar Bay | 108197 | 54344 |
| Port Royal | 13985 | 6969 |
| Fire Strike | 53566 | 29561 |
| Night Raid | 170143 | 109366 |
| Background Blur | 371.2 frames/s | 185.1 frames/s |
| Face Detection | 235 frames/s | 108.4 frames/s |
| Horizon Detection | 7.51 Gpix/sec | 5.35 Gpix/sec |
| Edge Detection | 10.6 Gpix/sec | 7.17 Gpix/sec |
| Gaussian Blur | 12.4 Gpix/sec | 5.54 Gpix/sec |
| Feature Matching | 2.03 Gpix/sec | 1.15 Gpix/sec |
| Stereo Matching | 1120 Gpix/sec | 478 Gpix/sec |
| Particle Physics | 30420.2 fps | 15183 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 1197 | 988 |
| DirectX 11 | 289 fps | 163 fps |
| DirectX 12 | 115 fps | 79 fps |
| GPU Compute | 18571 Ops/s | 10075 Ops/s |
| Aztec Ruins (Normal) | 1246.5 fps | 733.4 fps |
| Car Chase | 1077.7 fps | 614.3 fps |
| Manhattan 3.1.1 (1440p) | 884.8 fps | 523.6 fps |
| T-Rex | 4829.9 fps | 2676.1 fps |
| ALU 2 | 8110.1 fps | 3657.2 fps |
| Driver Overhead 2 | 285.3 fps | 282.8 fps |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
| Tessellation | 7994.7 | 3670 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Announced | January, 3, 2023 | December, 2, 2020 |
| Form Factor | PC use | PC use |
| Use case | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ada Lovelace | Ampere |
| Codename | AD104 | GA104 |
| Price | 799 | 399 |
GPU
| GPU Frequency | 2310 MHz | 1410 MHz |
| Boost GPU Frequency | 2610 MHz | 1665 MHz |
| Shader Units | 7680 | 4864 |
| TMUs | 240 | 152 |
| ROPs | 80 | 80 |
| Execution Units | 60 | 38 |
| Ray Tracing Cores | 60 | 38 |
| Tensor Cores | 240 | 152 |
| L1 cache | 128 KB/core | 128 KB/core |
| L2 cache | 48000 KB/core | 4000 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 209 Gpix/sec | 133 Gpix/sec |
| Texture Fill Rate | 626 GTex/s | 253 GTex/s |
| FLOPS | 40.1 TFLOPS | 16.2 TFLOPS |
Process
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 285 W | 200 W |
| Process | TSMC | Samsung |
| Process tech. | 5 nm | 8 nm |
| Transistor Size | 294 mm² | 392 mm² |
| Transistor count | 35 billion | 17 billion |
| Transistor density | 119.05 MTr/mm² | 43.37 MTr/mm² |
Memory
| Interface | GDDR6X | GDDR6 |
| Memory Frequency | 1313 MHz | 1750 MHz |
| Bus | 192 bit | 256 bit |
| ECC support | No | No |
| Effective Memory Speed | 21000 MB/s | 14000 MB/s |
| Memory Size | 12 GB | 8 GB |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| CUDA | 8.9 | 8.6 |
| DisplayPort | 1.4a | 1.4a |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 2 |
Results
After analyzing the data, we consider Nvidia GeForce RTX 4070 Ti the clear winner in this comparison.
Survey
Total Votes: 9
