Quick/Comparisons
39 | Gaming | 71 |
45 | Workstation | 73 |
35 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →60 |
39 | Energy Efficiency | 50 |
40 | Quick Comparison Final Score | 67 |
| GA104 (GN20-E7) | Graphics Processor | GB203-400 |
| 6144 | Cores | 10496 |
| 192 / 96 | TMUs / ROPs | 328 / 112 |
| 3258.81 | Blender GPU | 8001.96 |
| 84 | Forza Horizon 5 | 154 |
| 127 | The Witcher 3 | 198 |
| 165 | Counter-Strike 2 | 213 |
| 104 | Far Cry 6 | 155 |
| 70 | Hogwarts Legacy | 123 |
| 98 | Call of Duty | 187 |
| 66 | Ghost of Tsushima | 115 |
| 84 | Cyberpunk 2077 | 155 |
| 129 | Tomb Raider | 260 |
| 103 | Average FPS | 173 |
| 125 | 1080p High | 202 |
| 103 | 1080p Ultra | 173 |
| 76 | 1440p Ultra | 137 |
| 44 | 4K Ultra | 80 |
| Low | Margin of Error | Low |
| 128827 | GB6 Compute Score | 226752 |
| 211 img/sec | Background Blur | 266.5 img/sec |
| 123.6 img/sec | Face Detection | 196.9 img/sec |
| 5.78 Gpixels/sec | Horizon Detection | 10.6 Gpixels/sec |
| 8.03 Gpixels/sec | Edge Detection | 15.2 Gpixels/sec |
| 6.25 Gpixels/sec | Gaussian Blur | 14.4 Gpixels/sec |
| 1.17 Gpixels/sec | Feature Matching | 1.89 Gpixels/sec |
| 543.2 Gpixels/sec | Stereo Matching | 1150 Gpixels/sec |
| 17774.9 FPS | Particle Physics | 29783 FPS |
| OpenCL | API | OpenCL |
| 16147 | G3D Mark Score | 28298 |
| 630 | G2D Mark | 1094 |
| 145 FPS | DirectX 11 | 265 FPS |
| 71 FPS | DirectX 12 | 136 FPS |
| 7126 Ops/s | GPU Compute | 11559 Ops/s |
| 18354 | GB6 ML Single Precision | 30250 |
| 29767 | GB6 ML Half Precision | 52126 |
| 11487 | GB6 ML Quantized | 23496 |
| 6773 | Image Classification (SP) | 12121 |
| 19587 | Image Segmentation (HP) | 33054 |
| 15553 | Image Super Resolution (Q) | 33652 |
| 35885 | Face Detection (HP) | 67213 |
| 82446 | Pose Estimation (Q) | 151395 |
| 2830 | Text Classification (SP) | 3209 |
| 4019 | Machine Translation (HP) | 6292 |
| 8380 | Object Detection (SP) | 15618 |
| 28597 | Depth Estimation (Q) | 57894 |
| 184715 | Style Transfer (SP) | 272117 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 120-164 GPixel/s | Pixel Fill Rate | 170-242 GPixel/s |
| 239-328 GTexel/s | Texture Fill Rate | 497-708 GTexel/s |
| 15.3-21 TFLOPS | FLOPS (FP32) | 31.8-45.3 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 8-16 GB | Memory Size | 24 GB |
| 1500-1750 MHz | Memory Clock | 1750 MHz |
| 12000-14000 Mbps | Effective Memory Speed | 28000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 896 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 80-165 W (configurable) | TGP | 95-175 W (configurable) |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 4 nm |
| 392 mm² | Die Size | 378 mm² |
| 17.4 billion | Transistor Count | 45.6 billion |
| 44.39 MTr/mm² | Transistor Density | 120.63 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 2 | OpenCL | 3 |
| 8.6 | CUDA | 10.1 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 12, 2021 | Released | January 6, 2025 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | Blackwell 2.0 |
| GA104 (GN20-E7) | GPU Codename | GB203-400 |
| -Intel Core i9 12900Hor above | Recommended CPU | -Intel Core Ultra 9 275HXor above |
| 11592 | Steel Nomad Lite Score | 26140 |
| 11991 | Time Spy | 25013 |
| 50371 | Solar Bay | 115677 |
| 7201 | Port Royal | 16533 |
| 29067 | Fire Strike | 51096 |
| 24760 | Wild Life Extreme | 47099 |
| 81949 | Night Raid | 177139 |
| 780-1350 MHz (configurable) | Base Clock | 990-1515 MHz (configurable) |
| 1245-1710 MHz (configurable) | Boost Clock | 1515-2160 MHz (configurable) |
| 6144 | Shading Units | 10496 |
| 192 | Texture Mapping Units (TMUs) | 328 |
| 96 | Render Output Units (ROPs) | 112 |
| 48 | Compute Units (Pipelines) | 82 |
| 192 | Tensor Cores | 328 |
| 48 | Ray-tracing Cores | 82 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |