Quick/Comparisons
34 | Gaming | 4 |
32 | Workstation | 12 |
21 | AI/ML |
Compare with something else?
Compare Nvidia RTX Pro with another →4 |
78 | Energy Efficiency | 71 |
39 | Quick Comparison Final Score | 17 |
| GB207-300-A1 | Graphics Processor | Raven |
| 1792 | Cores | 640 |
| 56 / 24 | TMUs / ROPs | 40 / 16 |
| 2128.65 | Blender GPU | 76.12 |
| — | Forza Horizon 5 | - |
| — | The Witcher 3 | — |
| — | Counter-Strike 2 | 13 |
| — | Far Cry 6 | - |
| — | Hogwarts Legacy | — |
| — | Call of Duty | 11 |
| — | Ghost of Tsushima | - |
| — | Cyberpunk 2077 | — |
| — | Tomb Raider | 10 |
| — | Average FPS | - |
| — | 1080p High | 11 |
| — | 1080p Ultra | - |
| — | 1440p Ultra | - |
| — | 4K Ultra | - |
| — | Margin of Error | Low |
| 66956 | GB6 Compute Score | 11268 |
| 112.8 img/sec | Background Blur | 25.3 img/sec |
| 66.5 img/sec | Face Detection | 12.1 img/sec |
| 2.36 Gpixels/sec | Horizon Detection | 0.39 Gpixels/sec |
| 3 Gpixels/sec | Edge Detection | 0.62 Gpixels/sec |
| 3.67 Gpixels/sec | Gaussian Blur | 0.49 Gpixels/sec |
| 0.85 Gpixels/sec | Feature Matching | 0.15 Gpixels/sec |
| 287.1 Gpixels/sec | Stereo Matching | 38 Gpixels/sec |
| 9494.1 FPS | Particle Physics | 1381 FPS |
| OpenCL | API | OpenCL |
| 13205 | G3D Mark Score | 1500 |
| 702 | G2D Mark | 338 |
| 99 FPS | DirectX 11 | 9 FPS |
| 69 FPS | DirectX 12 | 8 FPS |
| 5058 Ops/s | GPU Compute | 827 Ops/s |
| 11766 | GB6 ML Single Precision | 2156 |
| 23687 | GB6 ML Half Precision | 2805 |
| 9527 | GB6 ML Quantized | 1656 |
| 4878 | Image Classification (SP) | 938 |
| 15282 | Image Segmentation (HP) | 1144 |
| 12309 | Image Super Resolution (Q) | 2094 |
| 27767 | Face Detection (HP) | 3148 |
| 44436 | Pose Estimation (Q) | 6847 |
| 2471 | Text Classification (SP) | 625 |
| 3958 | Machine Translation (HP) | 1118 |
| 6278 | Object Detection (SP) | 1039 |
| 23945 | Depth Estimation (Q) | 3791 |
| 70513 | Style Transfer (SP) | 13640 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 43-56 GPixel/s | Pixel Fill Rate | 21-22 GPixel/s |
| 100-131 GTexel/s | Texture Fill Rate | 52-56 GTexel/s |
| 6.4-8.4 TFLOPS | FLOPS (FP32) | 1.7-1.8 TFLOPS |
| GDDR7 | Memory Type | System Shared |
| 6 GB | Memory Size | System RAM Dependent |
| 1500 MHz | Memory Clock | System RAM Dependent |
| 24000 Mbps | Effective Memory Speed | System RAM Dependent |
| 96-bit | Bus | — |
| No | ECC | No |
| 288 GB/s | Memory Bandwidth | — |
| PCIe 5.0 x16 | Interface | IGP |
| 35-75 W (configurable) | TGP | 15 W |
| TSMC | Manufacturing | GlobalFoundries |
| 5 nm | Fabrication Process | 14 nm |
| 149 mm² | Die Size | 210 mm² |
| 16.9 billion | Transistor Count | 4.94 billion |
| 113.42 MTr/mm² | Transistor Density | 23.52 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2 |
| 12 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | — |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| March 18, 2025 | Released | October 26, 2017 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Entry-level | Segment | Entry-level |
| Blackwell 2.0 | Architecture | GCN 5.0 |
| GB207-300-A1 | GPU Codename | Raven |
| -Intel Core Ultra 7 255Hor above | Recommended CPU | -AMD Ryzen 7 3700Uor above |
| — | Steel Nomad Lite Score | 789 |
| — | Time Spy | 770 |
| — | Solar Bay | — |
| — | Port Royal | — |
| — | Fire Strike | 2597 |
| — | Wild Life Extreme | 1532 |
| — | Night Raid | 9616 |
| 1357-1792 MHz (configurable) | Base Clock | 300 MHz |
| 1792-2332 MHz (configurable) | Boost Clock | 1300-1400 MHz (configurable) |
| 1792 | Shading Units | 640 |
| 56 | Texture Mapping Units (TMUs) | 40 |
| 24 | Render Output Units (ROPs) | 16 |
| 14 | Compute Units (Pipelines) | 10 |
| 56 | Tensor Cores | No |
| 14 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 24MB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |