GeForce RTX 4080 SUPER vs 3090 Ti
VS
We compared two discrete desktop gaming GPUs: the GeForce RTX 4080 SUPER 16 GB with 80 pipelines and 10240 shaders against the 1 year and 11 months older RTX 3090 Ti 24 GB that utilizes 84 pipelines and 10752 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 4080 SUPER
- Performs better (up to 26%) in 3DMark Steel Nomad Lite
- Manufactured using a more efficient 5 nm process technology
- Shows 17% higher average frame rate in modern games at QHD resolution – 149 vs 127 FPS
- 31% higher maximum theoretical performance (52.2 vs 40 TFLOPS)
- Supports Nvidia DLSS 3 technology
Reasons to consider the GeForce RTX 3090 Ti
- Includes 8 GB more video memory
- Has 37% higher memory bandwidth: 1008 vs 736.3 GB/s
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 231 166 153 123 |
200 136 126 99 |
| The Witcher 3 | 242 215 158 83 |
214 185 130 71 |
| Counter-Strike 2 | 302 227 167 85 |
286 213 154 85 |
| Far Cry 6 | 182 162 146 92 |
160 151 133 83 |
| Hogwarts Legacy | 166 136 110 60 |
141 116 93 52 |
| CoD: Modern Warfare III | 216 208 168 115 |
186 174 139 90 |
| Ghost of Tsushima | 146 125 111 71 |
129 105 89 57 |
| Cyberpunk 2077 | 199 174 123 59 |
158 140 98 44 |
| Shadow of the Tomb Raider | 288 266 201 112 |
254 237 183 101 |
| 1080p High | 219 | 192 |
| 1080p Ultra | 187 | 162 |
| 1440p Ultra | 149 | 127 |
| 4K Ultra | 89 | 76 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 28271 | 21855 |
| Solar Bay | 139050 | 109239 |
| Port Royal | 18353 | 14890 |
| Fire Strike | 63706 | 51935 |
| Wild Life Extreme | 59996 | 48861 |
| Night Raid | 180569 | 156537 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 279.5 img/sec | 362.7 img/sec |
| Face Detection | 220.1 img/sec | 227.9 img/sec |
| Horizon Detection | 11 Gpixels/sec | 11.3 Gpixels/sec |
| Edge Detection | 15.2 Gpixels/sec | 15.9 Gpixels/sec |
| Gaussian Blur | 16.2 Gpixels/sec | 12.1 Gpixels/sec |
| Feature Matching | 2.08 Gpixels/sec | 1.56 Gpixels/sec |
| Stereo Matching | 1370 Gpixels/sec | 1080 Gpixels/sec |
| Particle Physics | 37199.7 FPS | 31024.6 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1278 | 1226 |
| DirectX 11 | 300 FPS | 238 FPS |
| DirectX 12 | 135 FPS | 121 FPS |
| GPU Compute | 19597 Ops/s | 16494 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) | 12453 | 10246 |
| Image Segmentation (HP) | 34467 | 22830 |
| Image Super Resolution (Q) | 43534 | 23532 |
| Face Detection (HP) | 70300 | 48657 |
| Pose Estimation (Q) | 242331 | 147241 |
| Text Classification (SP) | 3767 | 2917 |
| Machine Translation (HP) | 6614 | 4427 |
| Object Detection (SP) | 18301 | 13323 |
| Depth Estimation (Q) | 66477 | 40055 |
| Style Transfer (SP) | 417906 | 298683 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 4080 SUPER and 3090 TiGeneral
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 31, 2024 | March 29, 2022 |
| Launch price (MSRP) | $999 | $1999 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ada Lovelace | Ampere |
| GPU Codename | AD103 | GA102 |
| Rival Equivalent | - Radeon RX 7900 XTX | - |
| Recommended CPU | - Intel Core i7 14700K or above | - Intel Core i9 12900K or above |
Desktop GPU rating (7th and 14th place)
Graphics Processing Unit
| Base Clock | 2295 MHz | 1560 MHz |
| Boost Clock | 2550 MHz | 1860 MHz |
| Shading Units | 10240 | 10752 |
| Texture Mapping Units (TMUs) | 320 | 336 |
| Render Output Units (ROPs) | 112 | 112 |
| Compute Units (Pipelines) | 80 | 84 |
| Tensor Cores | 320 | 336 |
| Ray-tracing Cores | 80 | 84 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 64MB shared | 6MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 286 GPixel/s | 208 GPixel/s |
| Texture Fill Rate | 816 GTexel/s | 625 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 320 W | 450 W |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 5 nm | 8 nm |
| Die Size | 379 mm² | 628 mm² |
| Transistor Count | 45 billion | 28 billion |
| Transistor Density | 118.73 MTr/mm² | 44.59 MTr/mm² |
Memory
| Memory Type | GDDR6X | GDDR6X |
| Memory Size | 16 GB | 24 GB |
| Memory Clock | 1438 MHz | 1313 MHz |
| Effective Memory Speed | 23000 Mbps | 21000 Mbps |
| Bus | 256-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 | 8.9 | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 2 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 33