Quick/Comparisons
31 | Gaming | 73 |
52 | Workstation | 62 |
31 | AI/ML |
Compare with something else?
Compare Nvidia RTX A4500 with another →67 |
48 | Energy Efficiency | 49 |
40 | Quick Comparison Final Score | 68 |
| GA104 | Graphics Processor | Navi 48 |
| 5888 | Cores | 4096 |
| 184 / 96 | TMUs / ROPs | 256 / 128 |
| 2757.5 | Blender GPU | 3176.42 |
| 71 | Forza Horizon 5 | 169 |
| 100 | The Witcher 3 | 236 |
| 137 | Counter-Strike 2 | 224 |
| 86 | Far Cry 6 | 178 |
| 56 | Hogwarts Legacy | 132 |
| 75 | Call of Duty | 234 |
| 52 | Ghost of Tsushima | 135 |
| 66 | Cyberpunk 2077 | 166 |
| 100 | Tomb Raider | 268 |
| 83 | Average FPS | 194 |
| 104 | 1080p High | 229 |
| 83 | 1080p Ultra | 194 |
| 60 | 1440p Ultra | 150 |
| 34 | 4K Ultra | 89 |
| High | Margin of Error | Low |
| 119474 | GB6 Compute Score | 182816 |
| 158.7 img/sec | Background Blur | 427.4 img/sec |
| 115.8 img/sec | Face Detection | 251 img/sec |
| 5.95 Gpixels/sec | Horizon Detection | 6.77 Gpixels/sec |
| 8.2 Gpixels/sec | Edge Detection | 9.42 Gpixels/sec |
| 5.85 Gpixels/sec | Gaussian Blur | 9.35 Gpixels/sec |
| 1.13 Gpixels/sec | Feature Matching | 1.42 Gpixels/sec |
| 505.2 Gpixels/sec | Stereo Matching | 651.4 Gpixels/sec |
| 15517.5 FPS | Particle Physics | 23630 FPS |
| OpenCL | API | OpenCL |
| 16804 | G3D Mark Score | 26904 |
| 714 | G2D Mark | 1319 |
| 131 FPS | DirectX 11 | 295 FPS |
| 77 FPS | DirectX 12 | 77 FPS |
| 6679 Ops/s | GPU Compute | 15995 Ops/s |
| 14763 | GB6 ML Single Precision | 39190 |
| 23628 | GB6 ML Half Precision | 55727 |
| 10163 | GB6 ML Quantized | 33599 |
| 6159 | Image Classification (SP) | 18001 |
| 12031 | Image Segmentation (HP) | 25174 |
| 15490 | Image Super Resolution (Q) | 45714 |
| 29614 | Face Detection (HP) | 74776 |
| 65582 | Pose Estimation (Q) | 196137 |
| 1918 | Text Classification (SP) | 5163 |
| 3097 | Machine Translation (HP) | 8677 |
| 8192 | Object Detection (SP) | 19602 |
| 23635 | Depth Estimation (Q) | 74879 |
| 142647 | Style Transfer (SP) | 411302 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 99-143 GPixel/s | Pixel Fill Rate | 380 GPixel/s |
| 190-273 GTexel/s | Texture Fill Rate | 760 GTexel/s |
| 12.2-17.5 TFLOPS | FLOPS (FP32) | 48.7 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 16 GB | Memory Size | 16 GB |
| 2000 MHz | Memory Clock | 2518 MHz |
| 16000 Mbps | Effective Memory Speed | 20100 Mbps |
| 256-bit | Bus | 256-bit |
| Yes | ECC | No |
| 512 GB/s | Memory Bandwidth | 640 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 80-140 W (configurable) | TGP | 304 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 4 nm |
| 392 mm² | Die Size | 356.5 mm² |
| 17.4 billion | Transistor Count | 53.9 billion |
| 44.39 MTr/mm² | Transistor Density | 151.19 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.6 | CUDA | No |
| Yes | Ray Tracing | Yes |
| — | DLSS | No |
| 1.4a | DisplayPort | 2.1a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| March 22, 2022 | Released | January 7, 2025 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | RDNA 4.0 |
| GA104 | GPU Codename | Navi 48 |
| -Intel Core i7 12800HXor above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 25494 | Fire Strike | 66381 |
| 8802 | Steel Nomad Lite Score | 26180 |
| 9410 | Time Spy | 29701 |
| 39802 | Solar Bay | 121225 |
| 6116 | Port Royal | 18525 |
| 19741 | Wild Life Extreme | 54685 |
| 93933 | Night Raid | 195698 |
| 510-1035 MHz (configurable) | Base Clock | 1660 MHz |
| 1035-1485 MHz (configurable) | Boost Clock | 2970 MHz |
| 5888 | Shading Units | 4096 |
| 184 | Texture Mapping Units (TMUs) | 256 |
| 96 | Render Output Units (ROPs) | 128 |
| 46 | Compute Units (Pipelines) | 64 |
| 184 | Tensor Cores | 128 |
| 46 | Ray-tracing Cores | 64 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |