Quick/Comparisons
A mid-range Nvidia RTX 3500 Laptop (Ada) graphics card with modest workstation performance (53/100). Suited for 1080p gaming and everyday tasks.
| Gaming | 43 /100 |
| Workstation | 53 /100 |
| AI/ML | 39 /100 |
| Energy Efficiency | 56 |
Looking for more comparisons?
Compare Nvidia RTX →| Quick Comparison Final Score | 47 /100 |
| Graphics Processor | AD104 |
| Cores | 5120 |
| TMUs / ROPs | 160 / 64 |
| Blender GPU | 4377.08 |
| Forza Horizon 5 | 93 |
| The Witcher 3 | 134 |
| Counter-Strike 2 | 191 |
| Far Cry 6 | 113 |
| Hogwarts Legacy | 80 |
| Call of Duty | 111 |
| Ghost of Tsushima | 72 |
| Cyberpunk 2077 | 89 |
| Tomb Raider | 145 |
| Average FPS | 114 |
| 1080p High | 138 |
| 1080p Ultra | 114 |
| 1440p Ultra | 84 |
| 4K Ultra | 49 |
| Margin of Error | High |
| GB6 Compute Score | 131037 |
| Background Blur | 223 img/sec |
| Face Detection | 145.8 img/sec |
| Horizon Detection | 5.87 Gpixels/sec |
| Edge Detection | 7.77 Gpixels/sec |
| Gaussian Blur | 7.2 Gpixels/sec |
| Feature Matching | 1.39 Gpixels/sec |
| Stereo Matching | 458.7 Gpixels/sec |
| Particle Physics | 14313 FPS |
| API | OpenCL |
| G3D Mark Score | 19719 |
| G2D Mark | 712 |
| DirectX 11 | 187 FPS |
| DirectX 12 | 83 FPS |
| GPU Compute | 7623 Ops/s |
| GB6 ML Single Precision | 20783 |
| GB6 ML Half Precision | 33871 |
| GB6 ML Quantized | 16429 |
| Image Classification (SP) | 8316 |
| Image Segmentation (HP) | 17301 |
| Image Super Resolution (Q) | 27105 |
| Face Detection (HP) | 38189 |
| Pose Estimation (Q) | 105500 |
| Text Classification (SP) | 3319 |
| Machine Translation (HP) | 3845 |
| Object Detection (SP) | 10208 |
| Depth Estimation (Q) | 38369 |
| Style Transfer (SP) | 196359 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 99-144 GPixel/s |
| Texture Fill Rate | 247-360 GTexel/s |
| FLOPS (FP32) | 15.8-23 TFLOPS |
| Memory Type | GDDR6 |
| Memory Size | 12 GB |
| Memory Clock | 2250 MHz |
| Effective Memory Speed | 18000 Mbps |
| Bus | 192-bit |
| ECC | Yes |
| Memory Bandwidth | 432 GB/s |
| Interface | PCIe 4.0 x16 |
| TGP | 60-140 W (configurable) |
| Manufacturing | TSMC |
| Fabrication Process | 5 nm |
| Die Size | 294 mm² |
| Transistor Count | 35.8 billion |
| Transistor Density | 121.77 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 8.9 |
| Ray Tracing | Yes |
| DLSS | DLSS 3 |
| DisplayPort | 1.4a |
| Vendor | Nvidia |
| Build | Discrete |
| Released | March 21, 2023 |
| Case | Laptop |
| Purpose | Professional |
| Segment | Mid-range |
| Architecture | Ada Lovelace |
| GPU Codename | AD104 |
| Recommended CPU | -Intel Core Ultra 7 165Hor above |
| Steel Nomad Lite Score | 13536 |
| Time Spy | 12966 |
| Solar Bay | 52474 |
| Port Royal | 7976 |
| Fire Strike | 32977 |
| Wild Life Extreme | 26514 |
| Night Raid | 110011 |
| Base Clock | — |
| Boost Clock | 1545-2250 MHz (configurable) |
| Shading Units | 5120 |
| Texture Mapping Units (TMUs) | 160 |
| Render Output Units (ROPs) | 64 |
| Compute Units (Pipelines) | 40 |
| Tensor Cores | 160 |
| Ray-tracing Cores | 40 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 48MB shared |
| Instructions Per Cycle | 2 IPC |
GeForce RTX 5080
84/100