Quick/Comparisons
76 | Gaming | 13 |
74 | Workstation | 22 |
66 | AI/ML |
Compare with something else?
Compare GeForce RTX 5070 with another →12 |
49 | Energy Efficiency | 32 |
74 | Quick Comparison Final Score | 16 |
| GB203-200-A1 | Graphics Processor | Polaris 20 |
| 8960 | Cores | 2048 |
| 280 / 96 | TMUs / ROPs | 128 / 32 |
| 7584.67 | Blender GPU | 329.21 |
| 166 | Forza Horizon 5 | 36 |
| 213 | The Witcher 3 | 34 |
| 219 | Counter-Strike 2 | 43 |
| 159 | Far Cry 6 | 40 |
| 135 | Hogwarts Legacy | 22 |
| 205 | Call of Duty | 36 |
| 121 | Ghost of Tsushima | 21 |
| 174 | Cyberpunk 2077 | 26 |
| 260 | Tomb Raider | 42 |
| 184 | Average FPS | 33 |
| 217 | 1080p High | 45 |
| 184 | 1080p Ultra | 33 |
| 148 | 1440p Ultra | 23 |
| 86 | 4K Ultra | 12 |
| Low | Margin of Error | Low |
| 240508 | GB6 Compute Score | 37147 |
| 297.9 img/sec | Background Blur | 55.7 img/sec |
| 218.6 img/sec | Face Detection | 31.3 img/sec |
| 10.1 Gpixels/sec | Horizon Detection | 1.41 Gpixels/sec |
| 13.9 Gpixels/sec | Edge Detection | 2.82 Gpixels/sec |
| 14.8 Gpixels/sec | Gaussian Blur | 2.57 Gpixels/sec |
| 2.03 Gpixels/sec | Feature Matching | 0.31 Gpixels/sec |
| 1290 Gpixels/sec | Stereo Matching | 143.2 Gpixels/sec |
| 35438.3 FPS | Particle Physics | 5080.1 FPS |
| OpenCL | API | OpenCL |
| 32425 | G3D Mark Score | 7922 |
| 1329 | G2D Mark | 724 |
| 304 FPS | DirectX 11 | 55 FPS |
| 126 FPS | DirectX 12 | 39 FPS |
| 18089 Ops/s | GPU Compute | 2890 Ops/s |
| 36504 | GB6 ML Single Precision | 6885 |
| 64459 | GB6 ML Half Precision | 7446 |
| 27312 | GB6 ML Quantized | 4931 |
| 14913 | Image Classification (SP) | 2676 |
| 45199 | Image Segmentation (HP) | 3757 |
| 39360 | Image Super Resolution (Q) | 6179 |
| 84188 | Face Detection (HP) | 10752 |
| 161400 | Pose Estimation (Q) | 35488 |
| 4010 | Text Classification (SP) | 1051 |
| 7973 | Machine Translation (HP) | 1933 |
| 18934 | Object Detection (SP) | 3048 |
| 67761 | Depth Estimation (Q) | 12040 |
| 335879 | Style Transfer (SP) | 71201 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 235 GPixel/s | Pixel Fill Rate | 40 GPixel/s |
| 687 GTexel/s | Texture Fill Rate | 159 GTexel/s |
| 43.9 TFLOPS | FLOPS (FP32) | 5.1 TFLOPS |
| GDDR7 | Memory Type | GDDR5 |
| 16 GB | Memory Size | 4 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 28000 Mbps | Effective Memory Speed | 7000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 896 GB/s | Memory Bandwidth | 224 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 3.0 x16 |
| 300 W | TGP | 150 W |
| TSMC | Manufacturing | GlobalFoundries |
| 4 nm | Fabrication Process | 14 nm |
| 378 mm² | Die Size | 232 mm² |
| 45.6 billion | Transistor Count | 5 billion |
| 120.63 MTr/mm² | Transistor Density | 21.55 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 12 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | 1.4a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| January 7, 2025 | Released | April 18, 2017 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Blackwell 2.0 | Architecture | GCN 4.0 |
| GB203-200-A1 | GPU Codename | Polaris 20 |
| -Intel Core Ultra 5 245Kor above | Recommended CPU | -Intel Core i5 8500or above |
| 29989 | Steel Nomad Lite Score | 3702 |
| 27815 | Time Spy | 3855 |
| 136964 | Solar Bay | — |
| 19613 | Port Royal | — |
| 67382 | Fire Strike | 13443 |
| 57734 | Wild Life Extreme | 7941 |
| 189734 | Night Raid | 50379 |
| 2295 MHz | Base Clock | 1168 MHz |
| 2452 MHz | Boost Clock | 1244 MHz |
| 8960 | Shading Units | 2048 |
| 280 | Texture Mapping Units (TMUs) | 128 |
| 96 | Render Output Units (ROPs) | 32 |
| 70 | Compute Units (Pipelines) | — |
| 280 | Tensor Cores | No |
| 70 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | 16KB per cluster |
| 48MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |