GeForce GTX 960
- Graphics Processor: GM206
- Cores: 1024
- TMUs / ROPs: 64 / 32
Review
Compare GeForce GTX 960 with other GPUs
Games
| Forza Horizon 5 | 29 14 13 - |
| The Witcher 3 | 24 18 13 - |
| Counter-Strike 2 | 46 29 19 - |
| Far Cry 6 | 31 27 16 10 |
| Hogwarts Legacy | 18 12 10 - |
| CoD: Modern Warfare III | 30 24 16 12 |
| Ghost of Tsushima | 15 - - - |
| Cyberpunk 2077 | 14 11 - - |
| Shadow of the Tomb Raider | 28 26 15 - |
| 1080p High | 26 |
| 1080p Ultra | 19 |
| 1440p Ultra | 13 |
| 4K Ultra | - |
| Margin of Error | Low |
Test in Benchmarks
Performance tests in graphics benchmarks and applications3D Mark
| Time Spy | 2302 |
| Fire Strike | 7720 |
| Wild Life Extreme | 4543 |
| Night Raid | 31121 |
GeekBench 6 OpenCL
| Background Blur | 51.7 img/sec |
| Face Detection | 26.1 img/sec |
| Horizon Detection | 0.84 Gpixels/sec |
| Edge Detection | 1.36 Gpixels/sec |
| Gaussian Blur | 1.26 Gpixels/sec |
| Feature Matching | 0.14 Gpixels/sec |
| Stereo Matching | 64.9 Gpixels/sec |
| Particle Physics | 1825 FPS |
| API | OpenCL |
Passmark Graphics
| G2D Mark | 677 |
| DirectX 11 | 42 FPS |
| DirectX 12 | 28 FPS |
| GPU Compute | 2801 Ops/s |
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
| Image Classification (SP) | 1492 |
| Image Segmentation (HP) | 2183 |
| Image Super Resolution (Q) | 3618 |
| Face Detection (HP) | 3654 |
| Pose Estimation (Q) | 11306 |
| Text Classification (SP) | 1315 |
| Machine Translation (HP) | 2085 |
| Object Detection (SP) | 1927 |
| Depth Estimation (Q) | 5491 |
| Style Transfer (SP) | 22683 |
| Framework | ONNX |
| Backend | DirectML |
Specifications
Detailed technical specifications of the GeForce GTX 960General
| Vendor | Nvidia |
| Build | Discrete |
| Released | January 22, 2015 |
| Launch price (MSRP) | $199 |
| Case | Desktop |
| Purpose | Gaming |
| Segment | Mid-range |
| Architecture | Maxwell 2.0 |
| GPU Codename | GM206 |
Desktop GPU rating - 90th place
Graphics Processing Unit
| Base Clock | 1127 MHz |
| Boost Clock | 1178 MHz |
| Shading Units | 1024 |
| Texture Mapping Units (TMUs) | 64 |
| Render Output Units (ROPs) | 32 |
| Compute Units (Pipelines) | 8 |
| Tensor Cores | No |
| Ray-tracing Cores | No |
| L1 Cache | 48KB per cluster |
| L2 Cache | 1MB shared |
| Instructions Per Cycle | 2 IPC |
Raw Performance
| Pixel Fill Rate | 38 GPixel/s |
| Texture Fill Rate | 75 GTexel/s |
Physical
| Interface | PCIe 3.0 x16 |
| TGP | 120 W |
| Manufacturing | TSMC |
| Fabrication Process | 28 nm |
| Die Size | 228 mm² |
| Transistor Count | 2 billion |
| Transistor Density | 8.77 MTr/mm² |
Memory
| Memory Type | GDDR5 |
| Memory Size | 2 GB |
| Memory Clock | 1753 MHz |
| Effective Memory Speed | 7000 Mbps |
| Bus | 128-bit |
| ECC | No |
API
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3.0 |
| CUDA | 5.2 |
| Ray Tracing | No |
| DLSS | No |
| DisplayPort | 1.2 |