Quick/Comparisons
37 | Gaming | 32 |
42 | Workstation | 33 |
32 | AI/ML |
Compare with something else?
Compare GeForce RTX 2080 with another →41 |
27 | Energy Efficiency | 66 |
38 | Quick Comparison Final Score | 39 |
| TU104 | Graphics Processor | Strix Halo |
| 3072 | Cores | 2560 |
| 192 / 64 | TMUs / ROPs | 160 / 64 |
| 2407.76 | Blender GPU | 1335.18 |
| 86 | Forza Horizon 5 | 77 |
| 121 | The Witcher 3 | 101 |
| 169 | Counter-Strike 2 | 138 |
| 105 | Far Cry 6 | 92 |
| 68 | Hogwarts Legacy | 61 |
| 97 | Call of Duty | 89 |
| 64 | Ghost of Tsushima | 64 |
| 82 | Cyberpunk 2077 | 65 |
| 131 | Tomb Raider | 115 |
| 103 | Average FPS | 89 |
| 124 | 1080p High | 114 |
| 103 | 1080p Ultra | 89 |
| 75 | 1440p Ultra | 64 |
| 42 | 4K Ultra | 34 |
| Low | Margin of Error | Low |
| 122905 | GB6 Compute Score | 93515 |
| 197.1 img/sec | Background Blur | 232.1 img/sec |
| 110.7 img/sec | Face Detection | 122.5 img/sec |
| 5.03 Gpixels/sec | Horizon Detection | 2.92 Gpixels/sec |
| 6.5 Gpixels/sec | Edge Detection | 4.07 Gpixels/sec |
| 7.05 Gpixels/sec | Gaussian Blur | 3.49 Gpixels/sec |
| 1.28 Gpixels/sec | Feature Matching | 1.08 Gpixels/sec |
| 576.8 Gpixels/sec | Stereo Matching | 396.3 Gpixels/sec |
| 15732.9 FPS | Particle Physics | 13016.5 FPS |
| OpenCL | API | OpenCL |
| 19452 | G3D Mark Score | 18115 |
| 919 | G2D Mark | 1172 |
| 167 FPS | DirectX 11 | 157 FPS |
| 75 FPS | DirectX 12 | 84 FPS |
| 8204 Ops/s | GPU Compute | 9062 Ops/s |
| 16090 | GB6 ML Single Precision | 22565 |
| 26121 | GB6 ML Half Precision | 30098 |
| 10870 | GB6 ML Quantized | 18100 |
| 6780 | Image Classification (SP) | 11176 |
| 15029 | Image Segmentation (HP) | 14027 |
| 15410 | Image Super Resolution (Q) | 27198 |
| 30849 | Face Detection (HP) | 40613 |
| 71857 | Pose Estimation (Q) | 92878 |
| 1983 | Text Classification (SP) | 4158 |
| 3417 | Machine Translation (HP) | 6473 |
| 8214 | Object Detection (SP) | 7431 |
| 26815 | Depth Estimation (Q) | 41825 |
| 148497 | Style Transfer (SP) | 190221 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 116 GPixel/s | Pixel Fill Rate | 186 GPixel/s |
| 348 GTexel/s | Texture Fill Rate | 464 GTexel/s |
| 11.2 TFLOPS | FLOPS (FP32) | 14.8 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | — |
| 1937 MHz | Memory Clock | — |
| 15500 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | — |
| 495.9 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x16 | Interface | PCIe 5.0 x16 |
| 250 W | TGP | 45-120 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 4 nm |
| 545 mm² | Die Size | 308 mm² |
| 13 billion | Transistor Count | — |
| 23.85 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 7.5 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| July 23, 2019 | Released | January 7, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Mid-range |
| Turing | Architecture | RDNA 3.5 |
| TU104 | GPU Codename | Strix Halo |
| -Intel Core i9 9900Kor above | Recommended CPU | -AMD Ryzen AI Max+ 395or above |
| 11569 | Steel Nomad Lite Score | 9818 |
| 11621 | Time Spy | 10010 |
| 52083 | Solar Bay | 46934 |
| 7001 | Port Royal | 5512 |
| 28788 | Fire Strike | 26722 |
| 23792 | Wild Life Extreme | 19043 |
| 108111 | Night Raid | 100428 |
| 1650 MHz | Base Clock | 1295 MHz |
| 1815 MHz | Boost Clock | 2900 MHz |
| 3072 | Shading Units | 2560 |
| 192 | Texture Mapping Units (TMUs) | 160 |
| 64 | Render Output Units (ROPs) | 64 |
| 48 | Compute Units (Pipelines) | 40 |
| 384 | Tensor Cores | No |
| 48 | Ray-tracing Cores | 40 |
| 64KB per cluster | L1 Cache | 512KB per cluster |
| 4MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |