Quick/Comparisons
The GeForce RTX 5080's exceptional gaming performance is unmatched by the Radeon 860M, thanks to its Blackwell 2.0 architecture and 16GB GDDR7 memory.
The GeForce RTX 5080's strong workstation performance and 16GB GDDR7 memory make it the clear winner for content creation tasks.
Although the Radeon 860M has dedicated AI tensor cores, the GeForce RTX 5080's capable AI/ML compute and Blackwell 2.0 architecture give it a slight edge in AI and machine learning tasks.
87 | Gaming | 9 |
85 | Workstation | 12 |
70 | AI/ML | 13 |
49 | Energy Efficiency | 86 |
84 | Quick Comparison Final Score | 23 |
| GB203-400 | Graphics Processor | Krackan Point |
| 10752 | Cores | 512 |
| 336 / 112 | TMUs / ROPs | 32 / 16 |
| 9138.54 | Blender GPU | 193.82 |
| 185 | Forza Horizon 5 | 24 |
| 237 | The Witcher 3 | 18 |
| 237 | Counter-Strike 2 | 26 |
| 176 | Far Cry 6 | 26 |
| 154 | Hogwarts Legacy | 12 |
| 241 | Call of Duty | 27 |
| 137 | Ghost of Tsushima | 12 |
| 190 | Cyberpunk 2077 | 13 |
| 270 | Tomb Raider | 22 |
| 203 | Average FPS | 20 |
| 239 | 1080p High | 26 |
| 203 | 1080p Ultra | 20 |
| 164 | 1440p Ultra | 14 |
| 97 | 4K Ultra | - |
| Low | Margin of Error | Low |
| 297747 | GB6 Compute Score | 22911 |
| 319.6 img/sec | Background Blur | 57.2 img/sec |
| 225 img/sec | Face Detection | 30.5 img/sec |
| 13.6 Gpixels/sec | Horizon Detection | 0.83 Gpixels/sec |
| 19.5 Gpixels/sec | Edge Detection | 1.16 Gpixels/sec |
| 20.4 Gpixels/sec | Gaussian Blur | 0.93 Gpixels/sec |
| 2.33 Gpixels/sec | Feature Matching | 0.35 Gpixels/sec |
| 1750 Gpixels/sec | Stereo Matching | 97.8 Gpixels/sec |
| 43676.6 FPS | Particle Physics | 3933.5 FPS |
| OpenCL | API | OpenCL |
| 35695 | G3D Mark Score | 4877 |
| 1407 | G2D Mark | 916 |
| 327 FPS | DirectX 11 | 37 FPS |
| 144 FPS | DirectX 12 | 24 FPS |
| 19397 Ops/s | GPU Compute | 2421 Ops/s |
| 38994 | GB6 ML Single Precision | 6947 |
| 66609 | GB6 ML Half Precision | 10338 |
| 29206 | GB6 ML Quantized | 5334 |
| 15441 | Image Classification (SP) | 2022 |
| 47173 | Image Segmentation (HP) | 3987 |
| 43223 | Image Super Resolution (Q) | 6657 |
| 92863 | Face Detection (HP) | 10337 |
| 202202 | Pose Estimation (Q) | 28437 |
| 3701 | Text Classification (SP) | 2326 |
| 7905 | Machine Translation (HP) | 4011 |
| 20955 | Object Detection (SP) | 1995 |
| 69068 | Depth Estimation (Q) | 12031 |
| 349205 | Style Transfer (SP) | 56710 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 293 GPixel/s | Pixel Fill Rate | 48 GPixel/s |
| 879 GTexel/s | Texture Fill Rate | 96 GTexel/s |
| 56.3 TFLOPS | FLOPS (FP32) | 3.1 TFLOPS |
| GDDR7 | Memory Type | System Shared |
| 16 GB | Memory Size | — |
| 1875 MHz | Memory Clock | — |
| 30000 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | — |
| 960 GB/s | Memory Bandwidth | — |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 360 W | TGP | 15-54 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 4 nm |
| 378 mm² | Die Size | 233 mm² |
| 45.6 billion | Transistor Count | 34 billion |
| 120.63 MTr/mm² | Transistor Density | 145.92 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 12 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 7, 2025 | Released | January 7, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Mid-range |
| Blackwell 2.0 | Architecture | RDNA 3.5 |
| GB203-400 | GPU Codename | Krackan Point |
| -Intel Core Ultra 7 265Kor above | Recommended CPU | -AMD Ryzen AI 7 350or above |
| 36200 | Steel Nomad Lite Score | 2112 |
| 32989 | Time Spy | 2565 |
| 160901 | Solar Bay | 11270 |
| 23257 | Port Royal | 1103 |
| 75518 | Fire Strike | 6835 |
| 69544 | Wild Life Extreme | 5150 |
| 200077 | Night Raid | 29003 |
| 2295 MHz | Base Clock | 600 MHz |
| 2617 MHz | Boost Clock | 3000 MHz |
| 10752 | Shading Units | 512 |
| 336 | Texture Mapping Units (TMUs) | 32 |
| 112 | Render Output Units (ROPs) | 16 |
| 84 | Compute Units (Pipelines) | 8 |
| 336 | Tensor Cores | No |
| 84 | Ray-tracing Cores | 8 |
| 128KB per cluster | L1 Cache | 512KB per cluster |
| 64MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 5080 with another →