Quick/Comparisons
64 | Gaming | 100 |
61 | Workstation | 93 |
54 | AI/ML |
Compare with something else?
Compare GeForce RTX 5070 with another →95 |
49 | Energy Efficiency | 49 |
61 | Quick Comparison Final Score | 96 |
| GB205-300 | Graphics Processor | GB202-300 |
| 6144 | Cores | 21760 |
| 192 / 80 | TMUs / ROPs | 680 / 176 |
| 6160.42 | Blender GPU | 15010.34 |
| 137 | Forza Horizon 5 | 244 |
| 187 | The Witcher 3 | 323 |
| 218 | Counter-Strike 2 | 265 |
| 146 | Far Cry 6 | 202 |
| 116 | Hogwarts Legacy | 207 |
| 176 | Call of Duty | 327 |
| 108 | Ghost of Tsushima | 179 |
| 140 | Cyberpunk 2077 | 229 |
| 236 | Tomb Raider | 299 |
| 163 | Average FPS | 253 |
| 193 | 1080p High | 294 |
| 163 | 1080p Ultra | 253 |
| 127 | 1440p Ultra | 207 |
| 75 | 4K Ultra | 124 |
| Low | Margin of Error | Low |
| 190967 | GB6 Compute Score | 419309 |
| 254.4 img/sec | Background Blur | 333 img/sec |
| 180.6 img/sec | Face Detection | 298.5 img/sec |
| 7.91 Gpixels/sec | Horizon Detection | 21.7 Gpixels/sec |
| 10.2 Gpixels/sec | Edge Detection | 33.7 Gpixels/sec |
| 10.7 Gpixels/sec | Gaussian Blur | 34.5 Gpixels/sec |
| 1.84 Gpixels/sec | Feature Matching | 2.53 Gpixels/sec |
| 975.7 Gpixels/sec | Stereo Matching | 2850 Gpixels/sec |
| 27816.5 FPS | Particle Physics | 59146.9 FPS |
| OpenCL | API | OpenCL |
| 28767 | G3D Mark Score | 38955 |
| 1300 | G2D Mark | 1413 |
| 280 FPS | DirectX 11 | 341 FPS |
| 106 FPS | DirectX 12 | 178 FPS |
| 14507 Ops/s | GPU Compute | 24632 Ops/s |
| 30221 | GB6 ML Single Precision | 53861 |
| 53037 | GB6 ML Half Precision | 81080 |
| 23474 | GB6 ML Quantized | 38938 |
| 12270 | Image Classification (SP) | 18948 |
| 30237 | Image Segmentation (HP) | 55109 |
| 35585 | Image Super Resolution (Q) | 58478 |
| 62662 | Face Detection (HP) | 114685 |
| 145190 | Pose Estimation (Q) | 344729 |
| 4198 | Text Classification (SP) | 4464 |
| 6233 | Machine Translation (HP) | 8184 |
| 16709 | Object Detection (SP) | 27802 |
| 58300 | Depth Estimation (Q) | 85572 |
| 246598 | Style Transfer (SP) | 687080 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 201 GPixel/s | Pixel Fill Rate | 424 GPixel/s |
| 482 GTexel/s | Texture Fill Rate | 1637 GTexel/s |
| 30.9 TFLOPS | FLOPS (FP32) | 104.8 TFLOPS |
| GDDR7 | Memory Type | GDDR7 |
| 12 GB | Memory Size | 32 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 28000 Mbps | Effective Memory Speed | 28000 Mbps |
| 192-bit | Bus | 512-bit |
| No | ECC | No |
| 672 GB/s | Memory Bandwidth | 1792 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 5.0 x16 |
| 250 W | TGP | 575 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 4 nm |
| 263 mm² | Die Size | 750 mm² |
| 31.1 billion | Transistor Count | 92.2 billion |
| 118.25 MTr/mm² | Transistor Density | 122.93 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 | January 7, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Blackwell 2.0 | Architecture | Blackwell 2.0 |
| GB205-300 | GPU Codename | GB202-300 |
| -Intel Core Ultra 5 245Kor above | Recommended CPU | -Intel Core Ultra 9 285Kor above |
| 23229 | Steel Nomad Lite Score | 52638 |
| 22678 | Time Spy | 46941 |
| 106731 | Solar Bay | 235224 |
| 14423 | Port Royal | 38113 |
| 58244 | Fire Strike | 87433 |
| 43724 | Wild Life Extreme | 108736 |
| 174956 | Night Raid | 207058 |
| 2160 MHz | Base Clock | 2017 MHz |
| 2512 MHz | Boost Clock | 2407 MHz |
| 6144 | Shading Units | 21760 |
| 192 | Texture Mapping Units (TMUs) | 680 |
| 80 | Render Output Units (ROPs) | 176 |
| 48 | Compute Units (Pipelines) | 170 |
| 192 | Tensor Cores | 680 |
| 48 | Ray-tracing Cores | 170 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 96MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |