Quick/Comparisons
76 | Gaming | 5 |
74 | Workstation | 15 |
66 | AI/ML |
Compare with something else?
Compare GeForce RTX 5070 with another →5 |
49 | Energy Efficiency | 79 |
74 | Quick Comparison Final Score | 20 |
| GB203-200-A1 | Graphics Processor | Tiger Lake GT2 |
| 8960 | Cores | 768 |
| 280 / 96 | TMUs / ROPs | 48 / 24 |
| 7584.67 | Blender GPU | — |
| 166 | Forza Horizon 5 | 9 |
| 213 | The Witcher 3 | 11 |
| 219 | Counter-Strike 2 | 12 |
| 159 | Far Cry 6 | 11 |
| 135 | Hogwarts Legacy | — |
| 205 | Call of Duty | 11 |
| 121 | Ghost of Tsushima | - |
| 174 | Cyberpunk 2077 | - |
| 260 | Tomb Raider | 13 |
| 184 | Average FPS | 10 |
| 217 | 1080p High | 13 |
| 184 | 1080p Ultra | 10 |
| 148 | 1440p Ultra | - |
| 86 | 4K Ultra | - |
| Low | Margin of Error | Low |
| 240508 | GB6 Compute Score | 17326 |
| 297.9 img/sec | Background Blur | 34.5 img/sec |
| 218.6 img/sec | Face Detection | 27.4 img/sec |
| 10.1 Gpixels/sec | Horizon Detection | 0.75 Gpixels/sec |
| 13.9 Gpixels/sec | Edge Detection | 1.11 Gpixels/sec |
| 14.8 Gpixels/sec | Gaussian Blur | 0.39 Gpixels/sec |
| 2.03 Gpixels/sec | Feature Matching | 0.18 Gpixels/sec |
| 1290 Gpixels/sec | Stereo Matching | 55.6 Gpixels/sec |
| 35438.3 FPS | Particle Physics | 3061.7 FPS |
| OpenCL | API | OpenCL |
| 32425 | G3D Mark Score | — |
| 1329 | G2D Mark | — |
| 304 FPS | DirectX 11 | — |
| 126 FPS | DirectX 12 | — |
| 18089 Ops/s | GPU Compute | — |
| 36504 | GB6 ML Single Precision | 3218 |
| 64459 | GB6 ML Half Precision | 3202 |
| 27312 | GB6 ML Quantized | 1996 |
| 14913 | Image Classification (SP) | 1428 |
| 45199 | Image Segmentation (HP) | 2420 |
| 39360 | Image Super Resolution (Q) | 1551 |
| 84188 | Face Detection (HP) | 3685 |
| 161400 | Pose Estimation (Q) | 6255 |
| 4010 | Text Classification (SP) | 938 |
| 7973 | Machine Translation (HP) | 1028 |
| 18934 | Object Detection (SP) | 1581 |
| 67761 | Depth Estimation (Q) | 4305 |
| 335879 | Style Transfer (SP) | 26119 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 235 GPixel/s | Pixel Fill Rate | 23-37 GPixel/s |
| 687 GTexel/s | Texture Fill Rate | 46-74 GTexel/s |
| 43.9 TFLOPS | FLOPS (FP32) | 1.5-2.4 TFLOPS |
| GDDR7 | Memory Type | System Shared |
| 16 GB | Memory Size | System RAM Dependent |
| 1750 MHz | Memory Clock | System RAM Dependent |
| 28000 Mbps | Effective Memory Speed | System RAM Dependent |
| 256-bit | Bus | — |
| No | ECC | No |
| 896 GB/s | Memory Bandwidth | — |
| PCIe 5.0 x16 | Interface | Ring Bus |
| 300 W | TGP | 15 W |
| TSMC | Manufacturing | Intel |
| 4 nm | Fabrication Process | 10 nm |
| 378 mm² | Die Size | 146 mm² |
| 45.6 billion | Transistor Count | — |
| 120.63 MTr/mm² | Transistor Density | — |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 12 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | — |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| January 7, 2025 | Released | August 15, 2020 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Blackwell 2.0 | Architecture | Generation 12.1 |
| GB203-200-A1 | GPU Codename | Tiger Lake GT2 |
| -Intel Core Ultra 5 245Kor above | Recommended CPU | -Intel Core i7 1160G7or above |
| 29989 | Steel Nomad Lite Score | 882 |
| 27815 | Time Spy | 1282 |
| 136964 | Solar Bay | — |
| 19613 | Port Royal | — |
| 67382 | Fire Strike | 4415 |
| 57734 | Wild Life Extreme | 3124 |
| 189734 | Night Raid | 14097 |
| 2295 MHz | Base Clock | 300 MHz |
| 2452 MHz | Boost Clock | 950-1550 MHz (configurable) |
| 8960 | Shading Units | 768 |
| 280 | Texture Mapping Units (TMUs) | 48 |
| 96 | Render Output Units (ROPs) | 24 |
| 70 | Compute Units (Pipelines) | 96 |
| 280 | Tensor Cores | — |
| 70 | Ray-tracing Cores | — |
| 128KB per cluster | L1 Cache | — |
| 48MB shared | L2 Cache | 1024KB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |