Quick/Comparisons
76 | Gaming | 9 |
74 | Workstation | 12 |
66 | AI/ML |
Compare with something else?
Compare GeForce RTX 5070 with another →15 |
49 | Energy Efficiency | 93 |
74 | Quick Comparison Final Score | 24 |
| GB203-200-A1 | Graphics Processor | Phoenix |
| 8960 | Cores | 512 |
| 280 / 96 | TMUs / ROPs | 32 / 16 |
| 7584.67 | Blender GPU | 258.41 |
| 166 | Forza Horizon 5 | 20 |
| 213 | The Witcher 3 | 20 |
| 219 | Counter-Strike 2 | 26 |
| 159 | Far Cry 6 | 24 |
| 135 | Hogwarts Legacy | 11 |
| 205 | Call of Duty | 26 |
| 121 | Ghost of Tsushima | 12 |
| 174 | Cyberpunk 2077 | 16 |
| 260 | Tomb Raider | 21 |
| 184 | Average FPS | 20 |
| 217 | 1080p High | 25 |
| 184 | 1080p Ultra | 20 |
| 148 | 1440p Ultra | 13 |
| 86 | 4K Ultra | - |
| Low | Margin of Error | Low |
| 240508 | GB6 Compute Score | 22589 |
| 297.9 img/sec | Background Blur | 57.8 img/sec |
| 218.6 img/sec | Face Detection | 28.7 img/sec |
| 10.1 Gpixels/sec | Horizon Detection | 0.8 Gpixels/sec |
| 13.9 Gpixels/sec | Edge Detection | 1 Gpixels/sec |
| 14.8 Gpixels/sec | Gaussian Blur | 0.82 Gpixels/sec |
| 2.03 Gpixels/sec | Feature Matching | 0.29 Gpixels/sec |
| 1290 Gpixels/sec | Stereo Matching | 85.4 Gpixels/sec |
| 35438.3 FPS | Particle Physics | 2844.5 FPS |
| OpenCL | API | OpenCL |
| 32425 | G3D Mark Score | 5374 |
| 1329 | G2D Mark | 894 |
| 304 FPS | DirectX 11 | 53 FPS |
| 126 FPS | DirectX 12 | 25 FPS |
| 18089 Ops/s | GPU Compute | 2877 Ops/s |
| 36504 | GB6 ML Single Precision | 8097 |
| 64459 | GB6 ML Half Precision | 11246 |
| 27312 | GB6 ML Quantized | 6004 |
| 14913 | Image Classification (SP) | 3449 |
| 45199 | Image Segmentation (HP) | 4098 |
| 39360 | Image Super Resolution (Q) | 7937 |
| 84188 | Face Detection (HP) | 12168 |
| 161400 | Pose Estimation (Q) | 29915 |
| 4010 | Text Classification (SP) | 2571 |
| 7973 | Machine Translation (HP) | 3852 |
| 18934 | Object Detection (SP) | 2687 |
| 67761 | Depth Estimation (Q) | 14163 |
| 335879 | Style Transfer (SP) | 59966 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 235 GPixel/s | Pixel Fill Rate | 42-45 GPixel/s |
| 687 GTexel/s | Texture Fill Rate | 83-90 GTexel/s |
| 43.9 TFLOPS | FLOPS (FP32) | 2.7-2.9 TFLOPS |
| GDDR7 | Memory Type | System Shared |
| 16 GB | Memory Size | — |
| 1750 MHz | Memory Clock | — |
| 28000 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | — |
| 896 GB/s | Memory Bandwidth | — |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x8 |
| 300 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 4 nm |
| 378 mm² | Die Size | 178 mm² |
| 45.6 billion | Transistor Count | 25.4 billion |
| 120.63 MTr/mm² | Transistor Density | 142.7 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 | Yes |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 7, 2025 | Released | January 4, 2023 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Blackwell 2.0 | Architecture | RDNA 3.0 |
| GB203-200-A1 | GPU Codename | Phoenix |
| -Intel Core Ultra 5 245Kor above | Recommended CPU | -AMD Ryzen 5 7640Uor above |
| 29989 | Steel Nomad Lite Score | 2061 |
| 27815 | Time Spy | 2373 |
| 136964 | Solar Bay | 9378 |
| 19613 | Port Royal | 975 |
| 67382 | Fire Strike | 7087 |
| 57734 | Wild Life Extreme | 4630 |
| 189734 | Night Raid | 29647 |
| 2295 MHz | Base Clock | 800 MHz |
| 2452 MHz | Boost Clock | 2600-2800 MHz (configurable) |
| 8960 | Shading Units | 512 |
| 280 | Texture Mapping Units (TMUs) | 32 |
| 96 | Render Output Units (ROPs) | 16 |
| 70 | Compute Units (Pipelines) | 8 |
| 280 | Tensor Cores | — |
| 70 | Ray-tracing Cores | 6 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |