Quick/Comparisons
64 | Gaming | 16 |
61 | Workstation | 25 |
54 | AI/ML |
Compare with something else?
Compare GeForce RTX 5070 with another →22 |
49 | Energy Efficiency | 100 |
61 | Quick Comparison Final Score | 33 |
| GB205-300 | Graphics Processor | Panther Lake |
| 6144 | Cores | 1536 |
| 192 / 80 | TMUs / ROPs | 48 / 24 |
| 6160.42 | Blender GPU | 1268.79 |
| 137 | Forza Horizon 5 | 38 |
| 187 | The Witcher 3 | 55 |
| 218 | Counter-Strike 2 | 60 |
| 146 | Far Cry 6 | 49 |
| 116 | Hogwarts Legacy | 21 |
| 176 | Call of Duty | 32 |
| 108 | Ghost of Tsushima | 25 |
| 140 | Cyberpunk 2077 | 33 |
| 236 | Tomb Raider | 52 |
| 163 | Average FPS | 41 |
| 193 | 1080p High | 52 |
| 163 | 1080p Ultra | 41 |
| 127 | 1440p Ultra | 29 |
| 75 | 4K Ultra | 14 |
| Low | Margin of Error | Low |
| 190967 | GB6 Compute Score | 64546 |
| 254.4 img/sec | Background Blur | — |
| 180.6 img/sec | Face Detection | — |
| 7.91 Gpixels/sec | Horizon Detection | — |
| 10.2 Gpixels/sec | Edge Detection | — |
| 10.7 Gpixels/sec | Gaussian Blur | — |
| 1.84 Gpixels/sec | Feature Matching | — |
| 975.7 Gpixels/sec | Stereo Matching | — |
| 27816.5 FPS | Particle Physics | — |
| OpenCL | API | — |
| 28767 | G3D Mark Score | 9029 |
| 1300 | G2D Mark | 786 |
| 280 FPS | DirectX 11 | 70 FPS |
| 106 FPS | DirectX 12 | 50 FPS |
| 14507 Ops/s | GPU Compute | 3702 Ops/s |
| 30221 | GB6 ML Single Precision | 11871 |
| 53037 | GB6 ML Half Precision | 20120 |
| 23474 | GB6 ML Quantized | 7879 |
| 12270 | Image Classification (SP) | 5487 |
| 30237 | Image Segmentation (HP) | 16864 |
| 35585 | Image Super Resolution (Q) | 8788 |
| 62662 | Face Detection (HP) | 25029 |
| 145190 | Pose Estimation (Q) | 18852 |
| 4198 | Text Classification (SP) | 2115 |
| 6233 | Machine Translation (HP) | 4266 |
| 16709 | Object Detection (SP) | 7449 |
| 58300 | Depth Estimation (Q) | 22207 |
| 246598 | Style Transfer (SP) | 95039 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 201 GPixel/s | Pixel Fill Rate | 60 GPixel/s |
| 482 GTexel/s | Texture Fill Rate | 120 GTexel/s |
| 30.9 TFLOPS | FLOPS (FP32) | 7.7 TFLOPS |
| GDDR7 | Memory Type | System Shared |
| 12 GB | Memory Size | — |
| 1750 MHz | Memory Clock | — |
| 28000 Mbps | Effective Memory Speed | — |
| 192-bit | Bus | — |
| No | ECC | No |
| 672 GB/s | Memory Bandwidth | — |
| PCIe 5.0 x16 | Interface | PCIe 5.0 |
| 250 W | TGP | — |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 3 nm |
| 263 mm² | Die Size | — |
| 31.1 billion | Transistor Count | — |
| 118.25 MTr/mm² | Transistor Density | — |
| 12.2 | DirectX | 12.1 |
| 1.4 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | 2.1 |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| January 7, 2025 | Released | January 5, 2026 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Blackwell 2.0 | Architecture | Celestial |
| GB205-300 | GPU Codename | Panther Lake |
| -Intel Core Ultra 5 245Kor above | Recommended CPU | -Intel Core Ultra X9 388Hor above |
| 23229 | Steel Nomad Lite Score | 4242 |
| 22678 | Time Spy | 6595 |
| 106731 | Solar Bay | 26399 |
| 14423 | Port Royal | 3886 |
| 58244 | Fire Strike | 16770 |
| 43724 | Wild Life Extreme | 11707 |
| 174956 | Night Raid | 68498 |
| 2160 MHz | Base Clock | 300 MHz |
| 2512 MHz | Boost Clock | 2500 MHz |
| 6144 | Shading Units | 1536 |
| 192 | Texture Mapping Units (TMUs) | 48 |
| 80 | Render Output Units (ROPs) | 24 |
| 48 | Compute Units (Pipelines) | 12 |
| 192 | Tensor Cores | — |
| 48 | Ray-tracing Cores | — |
| 128KB per cluster | L1 Cache | 64KB per cluster |
| 48MB shared | L2 Cache | 16MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |