Nvidia GeForce RTX 3070 Ti vs Nvidia GeForce RTX 3060
49
out 100
VS
33
out 100
Compared 2 processors: Nvidia GeForce RTX 3070 Ti, vs Nvidia GeForce RTX 3060. 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 | 156 102 93 68 | 110 67 60 39 |
 The Witcher 3 | 177 148 105 59 | 124 101 75 37 |
 Counter-Strike 2 | 261 198 140 81 | 184 131 96 47 |
 Far Cry 6 | 134 124 102 64 | 93 85 64 38 |
 Hogwarts Legacy | 104 85 65 36 | 68 56 40 20 |
 COD Modern Warfare 3 | 133 120 93 60 | 83 73 50 34 |
 Ghost of Tsushima | 94 79 63 36 | 65 48 37 21 |
 Cyberpunk 2077 | 115 102 63 29 | 69 61 36 15 |
 Shadow of the Tomb Raider | 178 165 125 68 | 107 98 68 37 |
| 1080p High | 150 | 100 |
| 1080p Ultra | 125 | 80 |
| 1440p Ultra | 94 | 58 |
| 4K Ultra | 56 | 32 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 14873 | 8748 |
| Solar Bay | 69827 | 40964 |
| Port Royal | 8880 | 5142 |
| Fire Strike | 37227 | 22308 |
| Night Raid | 133622 | 98831 |
| Background Blur | 197 frames/s | 149.6 frames/s |
| Face Detection | 128.1 frames/s | 91 frames/s |
| Horizon Detection | 6.56 Gpix/sec | 4.07 Gpix/sec |
| Edge Detection | 8.81 Gpix/sec | 5.58 Gpix/sec |
| Gaussian Blur | 6.47 Gpix/sec | 3.92 Gpix/sec |
| Feature Matching | 1.26 Gpix/sec | 1.01 Gpix/sec |
| Stereo Matching | 609.3 Gpix/sec | 372.9 Gpix/sec |
| Particle Physics | 18205 fps | 12226.3 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 1051 | 961 |
| DirectX 11 | 192 fps | 128 fps |
| DirectX 12 | 91 fps | 69 fps |
| GPU Compute | 11708 Ops/s | 8428 Ops/s |
| Aztec Ruins (Normal) | 865.5 fps | 555.5 fps |
| Car Chase | 699.5 fps | 492.3 fps |
| Manhattan 3.1.1 (1440p) | 610.7 fps | 407.9 fps |
| T-Rex | 3191.9 fps | 1940.6 fps |
| ALU 2 | 4526.7 fps | 2862.2 fps |
| Driver Overhead 2 | 288.3 fps | 295.2 fps |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
| Tessellation | 4520.6 | 2965.4 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Announced | June, 10, 2021 | January, 12, 2021 |
| Form Factor | PC use | PC use |
| Use case | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ampere | Ampere |
| Codename | GA104 | GA106 |
| Price | 599 | 329 |
GPU
| GPU Frequency | 1575 MHz | 1320 MHz |
| Boost GPU Frequency | 1770 MHz | 1777 MHz |
| Shader Units | 6144 | 3584 |
| TMUs | 192 | 112 |
| ROPs | 96 | 48 |
| Execution Units | 48 | 28 |
| Ray Tracing Cores | 48 | 28 |
| Tensor Cores | 192 | 112 |
| L1 cache | 128 KB/core | 128 KB/core |
| L2 cache | 4000 KB/core | 3000 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 170 Gpix/sec | 85 Gpix/sec |
| Texture Fill Rate | 340 GTex/s | 199 GTex/s |
| FLOPS | 21.7 TFLOPS | 12.7 TFLOPS |
Process
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 290 W | 170 W |
| Process | Samsung | Samsung |
| Process tech. | 8 nm | 8 nm |
| Transistor Size | 392 mm² | 276 mm² |
| Transistor count | 17 billion | 12 billion |
| Transistor density | 43.37 MTr/mm² | 43.48 MTr/mm² |
Memory
| Interface | GDDR6X | GDDR6 |
| Memory Frequency | 1188 MHz | 1875 MHz |
| Bus | 256 bit | 192 bit |
| ECC support | No | No |
| Effective Memory Speed | 19000 MB/s | 15000 MB/s |
| Memory Size | 8 GB | 12 GB |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| CUDA | 8.6 | 8.6 |
| DisplayPort | 1.4a | 1.4a |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 2 | DLSS 2 |
Results
After analyzing the data, we consider Nvidia GeForce RTX 3070 Ti the clear winner in this comparison.
Survey
Total Votes: 2
