Quick/Comparisons
A budget Nvidia GeForce GTX 980 Ti graphics card with limited performance overall, higher power consumption. Suited for casual gaming and basic graphics tasks.
| Gaming | 19 /100 |
| Workstation | 27 /100 |
| AI/ML | 13 /100 |
| Energy Efficiency | 1 |
Looking for more comparisons?
Compare GeForce GTX →| Quick Comparison Final Score | 21 /100 |
| Graphics Processor | GM200 |
| Cores | 2816 |
| TMUs / ROPs | 176 / 96 |
| Blender GPU | 536.2 |
| Forza Horizon 5 | 52 |
| The Witcher 3 | 64 |
| Counter-Strike 2 | 95 |
| Far Cry 6 | 63 |
| Hogwarts Legacy | 37 |
| Call of Duty | 47 |
| Ghost of Tsushima | 33 |
| Cyberpunk 2077 | 44 |
| Tomb Raider | 69 |
| Average FPS | 56 |
| 1080p High | 71 |
| 1080p Ultra | 56 |
| 1440p Ultra | 39 |
| 4K Ultra | 20 |
| Margin of Error | Low |
| GB6 Compute Score | 49950 |
| Background Blur | 134.8 img/sec |
| Face Detection | 59.8 img/sec |
| Horizon Detection | 2.37 Gpixels/sec |
| Edge Detection | 3.79 Gpixels/sec |
| Gaussian Blur | 3.46 Gpixels/sec |
| Feature Matching | 0.22 Gpixels/sec |
| Stereo Matching | 191.9 Gpixels/sec |
| Particle Physics | 4183.6 FPS |
| API | OpenCL |
| G3D Mark Score | 13642 |
| G2D Mark | 850 |
| DirectX 11 | 106 FPS |
| DirectX 12 | 55 FPS |
| GPU Compute | 6100 Ops/s |
| GB6 ML Single Precision | 7711 |
| GB6 ML Half Precision | 7464 |
| GB6 ML Quantized | 5338 |
| Image Classification (SP) | 3173 |
| Image Segmentation (HP) | 4916 |
| Image Super Resolution (Q) | 7407 |
| Face Detection (HP) | 8201 |
| Pose Estimation (Q) | 27221 |
| Text Classification (SP) | 1675 |
| Machine Translation (HP) | 2607 |
| Object Detection (SP) | 4123 |
| Depth Estimation (Q) | 11660 |
| Style Transfer (SP) | 55570 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 103 GPixel/s |
| Texture Fill Rate | 189 GTexel/s |
| FLOPS (FP32) | 6.1 TFLOPS |
| Memory Type | GDDR5 |
| Memory Size | 6 GB |
| Memory Clock | 1753 MHz |
| Effective Memory Speed | 7000 Mbps |
| Bus | 384-bit |
| ECC | No |
| Memory Bandwidth | 336.6 GB/s |
| Interface | PCIe 3.0 x16 |
| TGP | 250 W |
| Manufacturing | TSMC |
| Fabrication Process | 28 nm |
| Die Size | 601 mm² |
| Transistor Count | 8 billion |
| Transistor Density | 13.31 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 5.2 |
| Ray Tracing | No |
| DLSS | No |
| DisplayPort | 1.2 |
| Vendor | Nvidia |
| Build | Discrete |
| Released | June 2, 2015 |
| Case | Desktop |
| Purpose | Gaming |
| Segment | High-end |
| Architecture | Maxwell 2.0 |
| GPU Codename | GM200 |
| Recommended CPU | — |
| Steel Nomad Lite Score | 5945 |
| Time Spy | 5855 |
| Solar Bay | — |
| Port Royal | 3250 |
| Fire Strike | 19504 |
| Wild Life Extreme | 11830 |
| Night Raid | 70105 |
| Base Clock | 1000 MHz |
| Boost Clock | 1076 MHz |
| Shading Units | 2816 |
| Texture Mapping Units (TMUs) | 176 |
| Render Output Units (ROPs) | 96 |
| Compute Units (Pipelines) | 22 |
| Tensor Cores | No |
| Ray-tracing Cores | No |
| L1 Cache | 48KB per cluster |
| L2 Cache | 3MB shared |
| Instructions Per Cycle | 2 IPC |
84/100