Quick/Comparisons
35 | Gaming | 16 |
41 | Workstation | 25 |
34 | AI/ML |
Compare with something else?
Compare GeForce RTX 2080 with another →22 |
27 | Energy Efficiency | 100 |
37 | Quick Comparison Final Score | 33 |
| TU104 | Graphics Processor | Panther Lake |
| 2944 | Cores | 1536 |
| 184 / 64 | TMUs / ROPs | 48 / 24 |
| 2335.41 | Blender GPU | 1268.79 |
| 81 | Forza Horizon 5 | 38 |
| 120 | The Witcher 3 | 55 |
| 160 | Counter-Strike 2 | 60 |
| 99 | Far Cry 6 | 49 |
| 65 | Hogwarts Legacy | 21 |
| 93 | Call of Duty | 32 |
| 62 | Ghost of Tsushima | 25 |
| 75 | Cyberpunk 2077 | 33 |
| 123 | Tomb Raider | 52 |
| 98 | Average FPS | 41 |
| 119 | 1080p High | 52 |
| 98 | 1080p Ultra | 41 |
| 72 | 1440p Ultra | 29 |
| 40 | 4K Ultra | 14 |
| Low | Margin of Error | Low |
| 6.2 Gpixels/sec | Edge Detection | — |
| 6.56 Gpixels/sec | Gaussian Blur | — |
| 1.3 Gpixels/sec | Feature Matching | — |
| 499.7 Gpixels/sec | Stereo Matching | — |
| 15858.8 FPS | Particle Physics | — |
| OpenCL | API | — |
| 118637 | GB6 Compute Score | 64546 |
| 191.8 img/sec | Background Blur | — |
| 115.9 img/sec | Face Detection | — |
| 4.74 Gpixels/sec | Horizon Detection | — |
| 18607 | G3D Mark Score | 9029 |
| 900 | G2D Mark | 786 |
| 159 FPS | DirectX 11 | 70 FPS |
| 71 FPS | DirectX 12 | 50 FPS |
| 7761 Ops/s | GPU Compute | 3702 Ops/s |
| 17223 | GB6 ML Single Precision | 11871 |
| 28694 | GB6 ML Half Precision | 20120 |
| 11608 | GB6 ML Quantized | 7879 |
| 7122 | Image Classification (SP) | 5487 |
| 17897 | Image Segmentation (HP) | 16864 |
| 16120 | Image Super Resolution (Q) | 8788 |
| 34245 | Face Detection (HP) | 25029 |
| 69601 | Pose Estimation (Q) | 18852 |
| 2181 | Text Classification (SP) | 2115 |
| 4328 | Machine Translation (HP) | 4266 |
| 8748 | Object Detection (SP) | 7449 |
| 28373 | Depth Estimation (Q) | 22207 |
| 154510 | Style Transfer (SP) | 95039 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 109 GPixel/s | Pixel Fill Rate | 60 GPixel/s |
| 315 GTexel/s | Texture Fill Rate | 120 GTexel/s |
| 10.1 TFLOPS | FLOPS (FP32) | 7.7 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | — |
| 1750 MHz | Memory Clock | — |
| 14000 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x16 | Interface | PCIe 5.0 |
| 215 W | TGP | — |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 3 nm |
| 545 mm² | Die Size | — |
| 13 billion | Transistor Count | — |
| 23.85 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.1 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 7.5 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| September 20, 2018 | Released | January 5, 2026 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Turing | Architecture | Celestial |
| TU104 | GPU Codename | Panther Lake |
| -AMD Ryzen 9 9900Xor above | Recommended CPU | -Intel Core Ultra X9 388Hor above |
| 10886 | Steel Nomad Lite Score | 4242 |
| 11079 | Time Spy | 6595 |
| 49857 | Solar Bay | 26399 |
| 6459 | Port Royal | 3886 |
| 27671 | Fire Strike | 16770 |
| 22290 | Wild Life Extreme | 11707 |
| 100751 | Night Raid | 68498 |
| 1515 MHz | Base Clock | 300 MHz |
| 1710 MHz | Boost Clock | 2500 MHz |
| 2944 | Shading Units | 1536 |
| 184 | Texture Mapping Units (TMUs) | 48 |
| 64 | Render Output Units (ROPs) | 24 |
| 46 | Compute Units (Pipelines) | 12 |
| 368 | Tensor Cores | — |
| 46 | Ray-tracing Cores | — |
| 64KB per cluster | L1 Cache | 64KB per cluster |
| 4MB shared | L2 Cache | 16MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |