Nvidia GeForce RTX 3060 Ti vs Nvidia GeForce GTX 1070 Ti
41
out 100
VS
25
out 100
Compared 2 processors: Nvidia GeForce RTX 3060 Ti, vs Nvidia GeForce GTX 1070 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 | 132 85 77 55 | 94 56 49 29 |
 The Witcher 3 | 152 123 91 47 | 96 79 54 31 |
 Counter-Strike 2 | 226 170 122 67 | 149 108 79 37 |
 Far Cry 6 | 114 104 81 47 | 78 68 53 27 |
 Hogwarts Legacy | 86 70 55 26 | 50 43 32 16 |
 COD Modern Warfare 3 | 109 99 69 45 | 64 55 37 23 |
 Ghost of Tsushima | 82 66 48 30 | 47 38 30 13 |
 Cyberpunk 2077 | 92 83 51 23 | 53 47 26 13 |
 Shadow of the Tomb Raider | 139 129 97 52 | 87 76 55 27 |
| 1080p High | 126 | 80 |
| 1080p Ultra | 103 | 63 |
| 1440p Ultra | 77 | 46 |
| 4K Ultra | 44 | 24 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 11708 | 6843 |
| Solar Bay | 54344 | 18047 |
| Port Royal | 6969 | 1546 |
| Fire Strike | 29561 | 20114 |
| Night Raid | 109366 | 78421 |
| Background Blur | 185.1 frames/s | 149.2 frames/s |
| Face Detection | 108.4 frames/s | 67.6 frames/s |
| Horizon Detection | 5.35 Gpix/sec | 2.36 Gpix/sec |
| Edge Detection | 7.17 Gpix/sec | 3.57 Gpix/sec |
| Gaussian Blur | 5.54 Gpix/sec | 4.32 Gpix/sec |
| Feature Matching | 1.15 Gpix/sec | 0.27 Gpix/sec |
| Stereo Matching | 478 Gpix/sec | 209.6 Gpix/sec |
| Particle Physics | 15183 fps | 6584.9 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 988 | 875 |
| DirectX 11 | 163 fps | 107 fps |
| DirectX 12 | 79 fps | 51 fps |
| GPU Compute | 10075 Ops/s | 7163 Ops/s |
| Aztec Ruins (Normal) | 733.4 fps | 432.6 fps |
| Car Chase | 614.3 fps | 422.9 fps |
| Manhattan 3.1.1 (1440p) | 523.6 fps | 387.6 fps |
| T-Rex | 2676.1 fps | 2066.8 fps |
| ALU 2 | 3657.2 fps | 2265.2 fps |
| Driver Overhead 2 | 282.8 fps | 271.4 fps |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
| Tessellation | 3670 | 2590.8 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Announced | December, 2, 2020 | November, 2, 2017 |
| Form Factor | PC use | PC use |
| Use case | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ampere | Pascal |
| Codename | GA104 | GP104 |
| Price | 399 | n/a |
GPU
| GPU Frequency | 1410 MHz | 1607 MHz |
| Boost GPU Frequency | 1665 MHz | 1683 MHz |
| Shader Units | 4864 | 2432 |
| TMUs | 152 | 152 |
| ROPs | 80 | 64 |
| Execution Units | 38 | 19 |
| Ray Tracing Cores | 38 | No |
| Tensor Cores | 152 | No |
| L1 cache | 128 KB/core | 48 KB/core |
| L2 cache | 4000 KB/core | 2000 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 133 Gpix/sec | 108 Gpix/sec |
| Texture Fill Rate | 253 GTex/s | 256 GTex/s |
| FLOPS | 16.2 TFLOPS | 8.2 TFLOPS |
Process
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| TGP | 200 W | 180 W |
| Process | Samsung | TSMC |
| Process tech. | 8 nm | 16 nm |
| Transistor Size | 392 mm² | 314 mm² |
| Transistor count | 17 billion | 7 billion |
| Transistor density | 43.37 MTr/mm² | 22.29 MTr/mm² |
Memory
| Interface | GDDR6 | GDDR5 |
| Memory Frequency | 1750 MHz | 2002 MHz |
| Bus | 256 bit | 256 bit |
| ECC support | No | No |
| Effective Memory Speed | 14000 MB/s | 8000 MB/s |
| Memory Size | 8 GB | 8 GB |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| CUDA | 8.6 | 6.1 |
| DisplayPort | 1.4a | 1.4a |
| Ray Tracing | Yes | No |
| DLSS | DLSS 2 | No |
Results
After analyzing the data, we consider Nvidia GeForce RTX 3060 Ti the clear winner in this comparison.
Survey
Total Votes: 0
