GeForce RTX 3090 vs 3080 Ti
VS
Nvidia GeForce RTX 3090
GA102
We compared two discrete desktop gaming GPUs: the GeForce RTX 3090 24 GB with 82 pipelines and 10496 shaders against the 4 months newer RTX 3080 Ti 12 GB that utilizes 80 pipelines and 10240 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
DeviceFacts Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 3090
- Includes 12 GB more video memory
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 186 128 117 91 |
186 125 117 90 |
| The Witcher 3 | 205 170 128 66 |
204 173 125 67 |
| Counter-Strike 2 | 275 207 155 83 |
277 205 155 82 |
| Far Cry 6 | 156 145 124 77 |
153 142 123 75 |
| Hogwarts Legacy | 128 108 86 47 |
131 108 84 46 |
| CoD: Modern Warfare III | 171 159 123 80 |
169 158 121 82 |
| Ghost of Tsushima | 120 97 85 48 |
114 96 82 51 |
| Cyberpunk 2077 | 148 132 90 43 |
146 128 86 40 |
| Shadow of the Tomb Raider | 237 226 168 91 |
235 220 165 89 |
| 1080p High | 181 | 179 |
| 1080p Ultra | 152 | 151 |
| 1440p Ultra | 120 | 118 |
| 4K Ultra | 70 | 69 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 19896 | 19633 |
| Solar Bay | 97395 | 96626 |
| Port Royal | 13633 | 13265 |
| Fire Strike | 47512 | 47869 |
| Wild Life Extreme | 43669 | 42724 |
| Night Raid | 139766 | 145258 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 320.8 img/sec | 239.8 img/sec |
| Face Detection | 207.2 img/sec | 156.8 img/sec |
| Horizon Detection | 10.1 Gpixels/sec | 10.8 Gpixels/sec |
| Edge Detection | 14.4 Gpixels/sec | 14.8 Gpixels/sec |
| Gaussian Blur | 11.5 Gpixels/sec | 11.9 Gpixels/sec |
| Feature Matching | 1.48 Gpixels/sec | 1.53 Gpixels/sec |
| Stereo Matching | 984.2 Gpixels/sec | 889.6 Gpixels/sec |
| Particle Physics | 27764.9 FPS | 26054.6 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1069 | 1095 |
| DirectX 11 | 218 FPS | 221 FPS |
| DirectX 12 | 109 FPS | 109 FPS |
| GPU Compute | 15028 Ops/s | 14943 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 3090
No benchmark results yet
GeForce RTX 3080 Ti
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-10-09 -> Jjender | Steel Nomad Light | 23447 |
| 📘 2025-11-01 (cancel) | Cinebench 2024 | 15466 |
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) | 10665 | 9747 |
| Image Segmentation (HP) | 28963 | 26654 |
| Image Super Resolution (Q) | 22697 | 21475 |
| Face Detection (HP) | 55232 | 49813 |
| Pose Estimation (Q) | 128155 | 135370 |
| Text Classification (SP) | 3152 | 2796 |
| Machine Translation (HP) | 5088 | 4757 |
| Object Detection (SP) | 13891 | 12924 |
| Depth Estimation (Q) | 37984 | 36756 |
| Style Transfer (SP) | 272000 | 274032 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 3090 and 3080 TiGeneral
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | September 24, 2020 | January 3, 2021 |
| Launch price (MSRP) | $1499 | $1199 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ampere | Ampere |
| GPU Codename | GA102 | GA102 |
| Rival Equivalent | - Radeon RX 6900 XT | - Radeon RX 6900 XT |
| Successor | - GeForce RTX 5090 | - |
| Recommended CPU | - Intel Core i9 12900K or above | - Intel Core i9 12900K or above |
Desktop GPU rating (20th and 23rd place)
Graphics Processing Unit
| Base Clock | 1395 MHz | 1365 MHz |
| Boost Clock | 1695 MHz | 1665 MHz |
| Shading Units | 10496 | 10240 |
| Texture Mapping Units (TMUs) | 328 | 320 |
| Render Output Units (ROPs) | 112 | 112 |
| Compute Units (Pipelines) | 82 | 80 |
| Tensor Cores | 328 | 320 |
| Ray-tracing Cores | 82 | 80 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 6MB shared | 6MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 190 GPixel/s | 186 GPixel/s |
| Texture Fill Rate | 556 GTexel/s | 533 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 350 W | 350 W |
| Manufacturing | Samsung | Samsung |
| Fabrication Process | 8 nm | 8 nm |
| Die Size | 628 mm² | 628 mm² |
| Transistor Count | 28 billion | 28 billion |
| Transistor Density | 44.59 MTr/mm² | 44.59 MTr/mm² |
Memory
| Memory Type | GDDR6X | GDDR6X |
| Memory Size | 24 GB | 12 GB |
| Memory Clock | 1219 MHz | 1188 MHz |
| Effective Memory Speed | 19500 Mbps | 19000 Mbps |
| Bus | 384-bit | 384-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 | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 2 | DLSS 2 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 58