Quick/Comparisons
The GeForce RTX 5070 Ti's superior gaming performance is due to its 16GB GDDR7 memory pool and Blackwell 2.0 architecture, outscoring the Nvidia RTX A3000 Laptop by 49 points.
Both GPUs have a strong presence in content creation, with the GeForce RTX 5070 Ti's 74 score closely matched by the Nvidia RTX A3000 Laptop's 40 score, resulting in a tie.
The GeForce RTX 5070 Ti's 66 score in AI/ML outperforms the Nvidia RTX A3000 Laptop's 22 score by 44 points, thanks to its dedicated hardware and architecture.
76 | Gaming | 27 |
74 | Workstation | 40 |
66 | AI/ML | 22 |
49 | Energy Efficiency | 49 |
74 | Quick Comparison Final Score | 34 |
| GB203-200-A1 | Graphics Processor | GA104 |
| 8960 | Cores | 4096 |
| 280 / 96 | TMUs / ROPs | 128 / 64 |
| 7584.67 | Blender GPU | 1953.57 |
| 166 | Forza Horizon 5 | 61 |
| 213 | The Witcher 3 | 90 |
| 219 | Counter-Strike 2 | 120 |
| 159 | Far Cry 6 | 76 |
| 135 | Hogwarts Legacy | 48 |
| 205 | Call of Duty | 63 |
| 121 | Ghost of Tsushima | 44 |
| 174 | Cyberpunk 2077 | 55 |
| 260 | Tomb Raider | 91 |
| 184 | Average FPS | 72 |
| 217 | 1080p High | 90 |
| 184 | 1080p Ultra | 72 |
| 148 | 1440p Ultra | 52 |
| 86 | 4K Ultra | 28 |
| Low | Margin of Error | High |
| 240508 | GB6 Compute Score | 89769 |
| 297.9 img/sec | Background Blur | 140.7 img/sec |
| 218.6 img/sec | Face Detection | 73 img/sec |
| 10.1 Gpixels/sec | Horizon Detection | 4.08 Gpixels/sec |
| 13.9 Gpixels/sec | Edge Detection | 5.52 Gpixels/sec |
| 14.8 Gpixels/sec | Gaussian Blur | 4.3 Gpixels/sec |
| 2.03 Gpixels/sec | Feature Matching | 0.9 Gpixels/sec |
| 1290 Gpixels/sec | Stereo Matching | 414.8 Gpixels/sec |
| 35438.3 FPS | Particle Physics | 12769.8 FPS |
| OpenCL | API | OpenCL |
| 32425 | G3D Mark Score | 12700 |
| 1329 | G2D Mark | 559 |
| 304 FPS | DirectX 11 | 103 FPS |
| 126 FPS | DirectX 12 | 57 FPS |
| 18089 Ops/s | GPU Compute | 5500 Ops/s |
| 36504 | GB6 ML Single Precision | 12265 |
| 64459 | GB6 ML Half Precision | 20980 |
| 27312 | GB6 ML Quantized | 8142 |
| 14913 | Image Classification (SP) | 4552 |
| 45199 | Image Segmentation (HP) | 11804 |
| 39360 | Image Super Resolution (Q) | 11986 |
| 84188 | Face Detection (HP) | 21457 |
| 161400 | Pose Estimation (Q) | 52678 |
| 4010 | Text Classification (SP) | 2248 |
| 7973 | Machine Translation (HP) | 2727 |
| 18934 | Object Detection (SP) | 6308 |
| 67761 | Depth Estimation (Q) | 20307 |
| 335879 | Style Transfer (SP) | 111653 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 235 GPixel/s | Pixel Fill Rate | 76-100 GPixel/s |
| 687 GTexel/s | Texture Fill Rate | 151-200 GTexel/s |
| 43.9 TFLOPS | FLOPS (FP32) | 9.7-12.8 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 16 GB | Memory Size | 6 GB |
| 1750 MHz | Memory Clock | 1375 MHz |
| 28000 Mbps | Effective Memory Speed | 11000 Mbps |
| 256-bit | Bus | 192-bit |
| No | ECC | Yes |
| 896 GB/s | Memory Bandwidth | 264 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 300 W | TGP | 60-130 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 4 nm | Fabrication Process | 8 nm |
| 378 mm² | Die Size | 392 mm² |
| 45.6 billion | Transistor Count | 17.4 billion |
| 120.63 MTr/mm² | Transistor Density | 44.39 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 2 |
| 2.1b | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 7, 2025 | Released | April 12, 2021 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | Mid-range |
| Blackwell 2.0 | Architecture | Ampere |
| GB203-200-A1 | GPU Codename | GA104 |
| -Intel Core Ultra 5 245Kor above | Recommended CPU | -Intel Core i7 12800HXor above |
| 29989 | Steel Nomad Lite Score | 8151 |
| 27815 | Time Spy | 7594 |
| 136964 | Solar Bay | 33550 |
| 19613 | Port Royal | 4542 |
| 67382 | Fire Strike | 19850 |
| 57734 | Wild Life Extreme | 3521 |
| 189734 | Night Raid | 75780 |
| 2295 MHz | Base Clock | 600-1080 MHz (configurable) |
| 2452 MHz | Boost Clock | 1180-1560 MHz (configurable) |
| 8960 | Shading Units | 4096 |
| 280 | Texture Mapping Units (TMUs) | 128 |
| 96 | Render Output Units (ROPs) | 64 |
| 70 | Compute Units (Pipelines) | 32 |
| 280 | Tensor Cores | 128 |
| 70 | Ray-tracing Cores | 32 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 5070 with another →