Quick/Comparisons
A mid-to-upper-range Nvidia GeForce RTX 5090 Laptop graphics card with capable workstation performance (73/100). Suited for 1440p/1080p gaming and content creation.
| Gaming | 71 /100 |
| Workstation | 73 /100 |
| AI/ML | 60 /100 |
| Energy Efficiency | 50 |
Looking for more comparisons?
Compare GeForce RTX →| Quick Comparison Final Score | 67 /100 |
| Graphics Processor | GB203-400 |
| Cores | 10496 |
| TMUs / ROPs | 328 / 112 |
| Blender GPU | 8001.96 |
| Forza Horizon 5 | 154 |
| The Witcher 3 | 198 |
| Counter-Strike 2 | 213 |
| Far Cry 6 | 155 |
| Hogwarts Legacy | 123 |
| Call of Duty | 187 |
| Ghost of Tsushima | 115 |
| Cyberpunk 2077 | 155 |
| Tomb Raider | 260 |
| Average FPS | 173 |
| 1080p High | 202 |
| 1080p Ultra | 173 |
| 1440p Ultra | 137 |
| 4K Ultra | 80 |
| Margin of Error | Low |
| GB6 Compute Score | 226752 |
| Background Blur | 266.5 img/sec |
| Face Detection | 196.9 img/sec |
| Horizon Detection | 10.6 Gpixels/sec |
| Edge Detection | 15.2 Gpixels/sec |
| Gaussian Blur | 14.4 Gpixels/sec |
| Feature Matching | 1.89 Gpixels/sec |
| Stereo Matching | 1150 Gpixels/sec |
| Particle Physics | 29783 FPS |
| API | OpenCL |
| G3D Mark Score | 28298 |
| G2D Mark | 1094 |
| DirectX 11 | 265 FPS |
| DirectX 12 | 136 FPS |
| GPU Compute | 11559 Ops/s |
| GB6 ML Single Precision | 30250 |
| GB6 ML Half Precision | 52126 |
| GB6 ML Quantized | 23496 |
| Image Classification (SP) | 12121 |
| Image Segmentation (HP) | 33054 |
| Image Super Resolution (Q) | 33652 |
| Face Detection (HP) | 67213 |
| Pose Estimation (Q) | 151395 |
| Text Classification (SP) | 3209 |
| Machine Translation (HP) | 6292 |
| Object Detection (SP) | 15618 |
| Depth Estimation (Q) | 57894 |
| Style Transfer (SP) | 272117 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 170-242 GPixel/s |
| Texture Fill Rate | 497-708 GTexel/s |
| FLOPS (FP32) | 31.8-45.3 TFLOPS |
| Memory Type | GDDR7 |
| Memory Size | 24 GB |
| Memory Clock | 1750 MHz |
| Effective Memory Speed | 28000 Mbps |
| Bus | 256-bit |
| ECC | No |
| Memory Bandwidth | 896 GB/s |
| Interface | PCIe 5.0 x16 |
| TGP | 95-175 W (configurable) |
| Manufacturing | TSMC |
| Fabrication Process | 4 nm |
| Die Size | 378 mm² |
| Transistor Count | 45.6 billion |
| Transistor Density | 120.63 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.4 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 10.1 |
| Ray Tracing | Yes |
| DLSS | DLSS 4 |
| DisplayPort | 2.1a |
| Vendor | Nvidia |
| Build | Discrete |
| Released | January 6, 2025 |
| Case | Laptop |
| Purpose | Gaming |
| Segment | High-end |
| Architecture | Blackwell 2.0 |
| GPU Codename | GB203-400 |
| Recommended CPU | -Intel Core Ultra 9 275HXor above |
| Steel Nomad Lite Score | 26140 |
| Time Spy | 25013 |
| Solar Bay | 115677 |
| Port Royal | 16533 |
| Fire Strike | 51096 |
| Wild Life Extreme | 47099 |
| Night Raid | 177139 |
| Base Clock | 990-1515 MHz (configurable) |
| Boost Clock | 1515-2160 MHz (configurable) |
| Shading Units | 10496 |
| Texture Mapping Units (TMUs) | 328 |
| Render Output Units (ROPs) | 112 |
| Compute Units (Pipelines) | 82 |
| Tensor Cores | 328 |
| Ray-tracing Cores | 82 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 64MB shared |
| Instructions Per Cycle | 2 IPC |
84/100