GeForce RTX 3060 Ti vs RTX 2080
VS
Nvidia GeForce RTX 2080
TU104
We compared two discrete desktop gaming GPUs: the GeForce RTX 3060 Ti with 38 pipelines and 4864 shaders against the 2 years and 3 months older RTX RTX 2080 that utilizes 46 pipelines and 2944 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 3060 Ti
- 60% higher maximum theoretical performance (16.2 vs 10.1 TFLOPS)
- Manufactured using a more efficient 8 nm process technology
- Shows 7% higher average frame rate in modern games at QHD resolution – 77 vs 72 FPS
- Has 65% more shading units (4864 vs 2944)
Reasons to consider the GeForce RTX 2080
- Features 216 more tensor cores for effective ML and AI workloads
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 132 88 75 54 |
127 80 71 48 |
| The Witcher 3 | 152 128 92 47 |
144 117 87 47 |
| Counter-Strike 2 | 226 169 121 64 |
213 162 116 62 |
| Far Cry 6 | 114 103 83 47 |
112 97 76 43 |
| Hogwarts Legacy | 86 73 55 29 |
80 65 52 25 |
| CoD: Modern Warfare III | 107 99 72 47 |
97 91 67 42 |
| Ghost of Tsushima | 82 69 48 28 |
78 63 46 27 |
| Cyberpunk 2077 | 92 81 48 22 |
86 78 47 21 |
| Shadow of the Tomb Raider | 139 132 95 53 |
129 122 89 45 |
| 1080p High | 126 | 118 |
| 1080p Ultra | 105 | 97 |
| 1440p Ultra | 77 | 72 |
| 4K Ultra | 43 | 40 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 11707 | 11077 |
| Solar Bay | 54429 | 49851 |
| Port Royal | 6971 | 6460 |
| Fire Strike | 29571 | 27672 |
| Wild Life Extreme | 24417 | 22307 |
| Night Raid | 109862 | 100912 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 185.1 img/sec | 191.8 img/sec |
| Face Detection | 108.4 img/sec | 115.9 img/sec |
| Horizon Detection | 5.35 Gpixels/sec | 4.74 Gpixels/sec |
| Edge Detection | 7.17 Gpixels/sec | 6.2 Gpixels/sec |
| Gaussian Blur | 5.54 Gpixels/sec | 6.56 Gpixels/sec |
| Feature Matching | 1.15 Gpixels/sec | 1.3 Gpixels/sec |
| Stereo Matching | 478 Gpixels/sec | 499.7 Gpixels/sec |
| Particle Physics | 15183 FPS | 15858.8 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 989 | 897 |
| DirectX 11 | 164 FPS | 160 FPS |
| DirectX 12 | 78 FPS | 71 FPS |
| GPU Compute | 9865 Ops/s | 7719 Ops/s |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 7384 | 7122 |
| Image Segmentation (HP) | 19320 | 17897 |
| Image Super Resolution (Q) | 16108 | 16120 |
| Face Detection (HP) | 34615 | 34245 |
| Pose Estimation (Q) | 74811 | 69601 |
| Text Classification (SP) | 2638 | 2181 |
| Machine Translation (HP) | 4136 | 4328 |
| Object Detection (SP) | 8718 | 8748 |
| Depth Estimation (Q) | 25946 | 28373 |
| Style Transfer (SP) | 153275 | 154510 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 3060 Ti and RTX 2080General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | December 2, 2020 | September 20, 2018 |
| Launch price (MSRP) | $399 | $699 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | High-end |
| Architecture | Ampere | Turing |
| GPU Codename | GA104 | TU104 |
| Rival Equivalent | - Radeon RX 6700 XT | - |
| Successor | - GeForce RTX 5060 Ti (8GB) | - GeForce RTX 5080 |
| Recommended CPU | - Intel Core i5 12600K or above | - AMD Ryzen 9 9900X or above |
Desktop GPU rating (49th and 51st place)
Graphics Processing Unit
| Base Clock | 1410 MHz | 1515 MHz |
| Boost Clock | 1665 MHz | 1710 MHz |
| Shading Units | 4864 | 2944 |
| Texture Mapping Units (TMUs) | 152 | 184 |
| Render Output Units (ROPs) | 80 | 64 |
| Compute Units (Pipelines) | 38 | 46 |
| Tensor Cores | 152 | 368 |
| Ray-tracing Cores | 38 | 46 |
| L1 Cache | 128KB per cluster | 64KB per cluster |
| L2 Cache | 4MB shared | 4MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 133 GPixel/s | 109 GPixel/s |
| Texture Fill Rate | 253 GTexel/s | 315 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| TGP | 200 W | 215 W |
| Manufacturing | Samsung | TSMC |
| Fabrication Process | 8 nm | 12 nm |
| Die Size | 392 mm² | 545 mm² |
| Transistor Count | 17 billion | 13 billion |
| Transistor Density | 43.37 MTr/mm² | 23.85 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 8 GB | 8 GB |
| Memory Clock | 1750 MHz | 1750 MHz |
| Effective Memory Speed | 14000 Mbps | 14000 Mbps |
| Bus | 256-bit | 256-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 8.6 | 7.5 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 2 | DLSS 2 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 37