Quick/Comparisons
The GeForce RTX 5070 Ti outperforms the Nvidia RTX Pro 3000 Laptop (Blackwell) in gaming due to its significantly higher score of 76 compared to 37.
The GeForce RTX 5070 Ti takes the lead in content creation with a score of 74, narrowly edging out the Nvidia RTX Pro 3000 Laptop (Blackwell) with a score of 59.
The GeForce RTX 5070 Ti excels in AI and machine learning tasks with a score of 66, outpacing the Nvidia RTX Pro 3000 Laptop (Blackwell) by a margin of 21 points.
76 | Gaming | 37 |
74 | Workstation | 59 |
66 | AI/ML | 45 |
49 | Energy Efficiency | 59 |
74 | Quick Comparison Final Score | 47 |
| GB203-200-A1 | Graphics Processor | GB205-300-A1 |
| 8960 | Cores | 5888 |
| 280 / 96 | TMUs / ROPs | 184 / 80 |
| 7584.67 | Blender GPU | 3405.25 |
| 166 | Forza Horizon 5 | 79 |
| 213 | The Witcher 3 | 111 |
| 219 | Counter-Strike 2 | 149 |
| 159 | Far Cry 6 | 94 |
| 135 | Hogwarts Legacy | 63 |
| 205 | Call of Duty | 83 |
| 121 | Ghost of Tsushima | 58 |
| 174 | Cyberpunk 2077 | 73 |
| 260 | Tomb Raider | 112 |
| 184 | Average FPS | 91 |
| 217 | 1080p High | 112 |
| 184 | 1080p Ultra | 91 |
| 148 | 1440p Ultra | 66 |
| 86 | 4K Ultra | 37 |
| Low | Margin of Error | High |
| 240508 | GB6 Compute Score | 167869 |
| 297.9 img/sec | Background Blur | 238.8 img/sec |
| 218.6 img/sec | Face Detection | 147.6 img/sec |
| 10.1 Gpixels/sec | Horizon Detection | 6.73 Gpixels/sec |
| 13.9 Gpixels/sec | Edge Detection | 9.27 Gpixels/sec |
| 14.8 Gpixels/sec | Gaussian Blur | 10.7 Gpixels/sec |
| 2.03 Gpixels/sec | Feature Matching | 1.68 Gpixels/sec |
| 1290 Gpixels/sec | Stereo Matching | 778.4 Gpixels/sec |
| 35438.3 FPS | Particle Physics | 23023.5 FPS |
| OpenCL | API | OpenCL |
| 32425 | G3D Mark Score | 21959 |
| 1329 | G2D Mark | 833 |
| 304 FPS | DirectX 11 | 224 FPS |
| 126 FPS | DirectX 12 | 100 FPS |
| 18089 Ops/s | GPU Compute | 7578 Ops/s |
| 36504 | GB6 ML Single Precision | 24473 |
| 64459 | GB6 ML Half Precision | 44496 |
| 27312 | GB6 ML Quantized | 18924 |
| 14913 | Image Classification (SP) | 9790 |
| 45199 | Image Segmentation (HP) | 28672 |
| 39360 | Image Super Resolution (Q) | 26553 |
| 84188 | Face Detection (HP) | 53161 |
| 161400 | Pose Estimation (Q) | 120306 |
| 4010 | Text Classification (SP) | 3406 |
| 7973 | Machine Translation (HP) | 5910 |
| 18934 | Object Detection (SP) | 12573 |
| 67761 | Depth Estimation (Q) | 47957 |
| 335879 | Style Transfer (SP) | 199379 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 235 GPixel/s | Pixel Fill Rate | 128-194 GPixel/s |
| 687 GTexel/s | Texture Fill Rate | 295-447 GTexel/s |
| 43.9 TFLOPS | FLOPS (FP32) | 18.9-28.6 TFLOPS |
| GDDR7 | Memory Type | GDDR7 |
| 16 GB | Memory Size | 12 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 28000 Mbps | Effective Memory Speed | 28000 Mbps |
| 256-bit | Bus | 192-bit |
| No | ECC | No |
| 896 GB/s | Memory Bandwidth | 672 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 5.0 x16 |
| 300 W | TGP | 60-140 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 5 nm |
| 378 mm² | Die Size | 263 mm² |
| 45.6 billion | Transistor Count | 31.1 billion |
| 120.63 MTr/mm² | Transistor Density | 118.25 MTr/mm² |
| 12.2 | DirectX | 12.2 |
| 1.4 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 4 |
| 2.1b | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 7, 2025 | Released | March 18, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | Mid-range |
| Blackwell 2.0 | Architecture | Blackwell 2.0 |
| GB203-200-A1 | GPU Codename | GB205-300-A1 |
| -Intel Core Ultra 5 245Kor above | Recommended CPU | -Intel Core Ultra 7 265HXor above |
| 29989 | Steel Nomad Lite Score | 8100 |
| 27815 | Time Spy | 12327 |
| 136964 | Solar Bay | 69295 |
| 19613 | Port Royal | — |
| 67382 | Fire Strike | 28339 |
| 57734 | Wild Life Extreme | — |
| 189734 | Night Raid | — |
| 2295 MHz | Base Clock | 848-1605 MHz (configurable) |
| 2452 MHz | Boost Clock | 1605-2430 MHz (configurable) |
| 8960 | Shading Units | 5888 |
| 280 | Texture Mapping Units (TMUs) | 184 |
| 96 | Render Output Units (ROPs) | 80 |
| 70 | Compute Units (Pipelines) | 46 |
| 280 | Tensor Cores | 184 |
| 70 | Ray-tracing Cores | 46 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 5070 with another →