GeForce RTX 3080 Ti vs 2080 Ti
VS
We compared two discrete desktop gaming GPUs: the GeForce RTX 3080 Ti 12 GB with 80 pipelines and 10240 shaders against the 2 years and 3 months older RTX 2080 Ti 11 GB that utilizes 68 pipelines and 4352 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 3080 Ti
- Performs significantly better (up to 50%) in 3DMark Steel Nomad Lite
- 2.5x higher maximum theoretical performance (34.1 vs 13.4 TFLOPS)
- Manufactured using a more efficient 8 nm process technology
- Shows 28% higher average frame rate in modern games at QHD resolution – 118 vs 92 FPS
- Has 48% higher memory bandwidth: 912 vs 616 GB/s
- Achieves 36% more points in the GeekBench 6 Compute test (196K vs 144K)
- Has 2.4x more shading units (10240 vs 4352)
Reasons to consider the GeForce RTX 2080 Ti
- Features 224 more tensor cores for effective ML and AI workloads
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 186 125 117 90 |
150 101 89 65 |
| The Witcher 3 | 204 173 125 67 |
175 142 104 55 |
| Counter-Strike 2 | 277 205 155 82 |
253 193 140 81 |
| Far Cry 6 | 153 142 123 75 |
132 122 101 61 |
| Hogwarts Legacy | 131 108 84 46 |
101 85 65 36 |
| CoD: Modern Warfare III | 169 158 121 82 |
124 117 85 56 |
| Ghost of Tsushima | 114 96 82 51 |
92 79 61 36 |
| Cyberpunk 2077 | 146 128 86 40 |
112 96 63 30 |
| Shadow of the Tomb Raider | 235 220 165 89 |
171 161 120 63 |
| 1080p High | 179 | 146 |
| 1080p Ultra | 151 | 122 |
| 1440p Ultra | 118 | 92 |
| 4K Ultra | 69 | 54 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 19633 | 14655 |
| Solar Bay | 96626 | 64022 |
| Port Royal | 13265 | 9109 |
| Fire Strike | 47869 | 35666 |
| Wild Life Extreme | 42724 | 29561 |
| Night Raid | 145258 | 115542 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 239.8 img/sec | 211 img/sec |
| Face Detection | 156.8 img/sec | 141.3 img/sec |
| Horizon Detection | 10.8 Gpixels/sec | 6.24 Gpixels/sec |
| Edge Detection | 14.8 Gpixels/sec | 8.1 Gpixels/sec |
| Gaussian Blur | 11.9 Gpixels/sec | 9.22 Gpixels/sec |
| Feature Matching | 1.53 Gpixels/sec | 1.46 Gpixels/sec |
| Stereo Matching | 889.6 Gpixels/sec | 627.3 Gpixels/sec |
| Particle Physics | 26054.6 FPS | 16980.5 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1095 | 926 |
| DirectX 11 | 221 FPS | 193 FPS |
| DirectX 12 | 109 FPS | 83 FPS |
| GPU Compute | 14943 Ops/s | 9831 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 3080 Ti
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-11-01 (cancel) | Cinebench 2024 | 15466 |
GeForce RTX 2080 Ti
No benchmark results yet
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) | 9747 | 8213 |
| Image Segmentation (HP) | 26654 | 19891 |
| Image Super Resolution (Q) | 21475 | 17598 |
| Face Detection (HP) | 49813 | 39785 |
| Pose Estimation (Q) | 135370 | 84003 |
| Text Classification (SP) | 2796 | 2062 |
| Machine Translation (HP) | 4757 | 4192 |
| Object Detection (SP) | 12924 | 10444 |
| Depth Estimation (Q) | 36756 | 31856 |
| Style Transfer (SP) | 274032 | 207773 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 3080 Ti and 2080 TiGeneral
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 3, 2021 | September 27, 2018 |
| Launch price (MSRP) | $1199 | $999 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ampere | Turing |
| GPU Codename | GA102 | TU102 |
| Rival Equivalent | - Radeon RX 6900 XT | - |
| Successor | - | - GeForce RTX 3080 Ti |
| Recommended CPU | - Intel Core i9 12900K or above | - Intel Core i9 9900K or above |
Desktop GPU rating (23rd and 40th place)
Graphics Processing Unit
| Base Clock | 1365 MHz | 1350 MHz |
| Boost Clock | 1665 MHz | 1545 MHz |
| Shading Units | 10240 | 4352 |
| Texture Mapping Units (TMUs) | 320 | 272 |
| Render Output Units (ROPs) | 112 | 88 |
| Compute Units (Pipelines) | 80 | 68 |
| Tensor Cores | 320 | 544 |
| Ray-tracing Cores | 80 | 68 |
| L1 Cache | 128KB per cluster | 64KB per cluster |
| L2 Cache | 6MB shared | 5632KB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 186 GPixel/s | 136 GPixel/s |
| Texture Fill Rate | 533 GTexel/s | 420 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| TGP | 350 W | 250 W |
| Manufacturing | Samsung | TSMC |
| Fabrication Process | 8 nm | 12 nm |
| Die Size | 628 mm² | 754 mm² |
| Transistor Count | 28 billion | 18 billion |
| Transistor Density | 44.59 MTr/mm² | 23.87 MTr/mm² |
Memory
| Memory Type | GDDR6X | GDDR6 |
| Memory Size | 12 GB | 11 GB |
| Memory Clock | 1188 MHz | 1750 MHz |
| Effective Memory Speed | 19000 Mbps | 14000 Mbps |
| Bus | 384-bit | 352-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: 8