GeForce GTX 1660 vs 1050 Ti
Nvidia GeForce GTX 1660
TU116
We compared two discrete desktop gaming GPUs: the GeForce GTX 1660 6 GB with 22 pipelines and 1408 shaders against the 2 years and 5 months older 1050 Ti 4 GB that utilizes 6 pipelines and 768 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the GeForce GTX 1660
- Performs significantly better (up to 2.2x) in 3DMark Steel Nomad Lite
- Shows 2.5x higher average frame rate in modern games at QHD resolution – 35 vs 14 FPS
- 2.4x higher maximum theoretical performance (5 vs 2.1 TFLOPS)
- Manufactured using a more efficient 12 nm process technology
- Includes 2 GB more video memory
- Achieves 2.8x more points in the GeekBench 6 Compute test (60K vs 21K)
- Has 71% higher memory bandwidth: 192.1 vs 112.1 GB/s
- Has 83% more shading units (1408 vs 768)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 81 45 36 24 |
31 16 15 9 |
| The Witcher 3 | 74 59 41 21 |
25 22 13 - |
| Counter-Strike 2 | 119 83 60 25 |
47 29 22 9 |
| Far Cry 6 | 66 56 44 21 |
33 29 18 9 |
| Hogwarts Legacy | 42 32 23 12 |
18 13 10 - |
| CoD: Modern Warfare III | 51 42 26 17 |
28 24 17 12 |
| Ghost of Tsushima | 37 30 20 11 |
15 9 - - |
| Cyberpunk 2077 | 40 36 22 9 |
15 13 - - |
| Shadow of the Tomb Raider | 68 62 43 20 |
29 26 17 - |
| 1080p High | 64 | 27 |
| 1080p Ultra | 49 | 20 |
| 1440p Ultra | 35 | 14 |
| 4K Ultra | 18 | - |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 5443 | 2351 |
| Solar Bay | 18104 | - |
| Port Royal | 1455 | - |
| Fire Strike | 14207 | 7702 |
| Wild Life Extreme | 10947 | 4901 |
| Night Raid | 66328 | 33499 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 107.7 img/sec | 56.6 img/sec |
| Face Detection | 58.6 img/sec | 27.4 img/sec |
| Horizon Detection | 2.07 Gpixels/sec | 0.82 Gpixels/sec |
| Edge Detection | 2.61 Gpixels/sec | 1.2 Gpixels/sec |
| Gaussian Blur | 3 Gpixels/sec | 1.27 Gpixels/sec |
| Feature Matching | 0.77 Gpixels/sec | 0.18 Gpixels/sec |
| Stereo Matching | 301.7 Gpixels/sec | 66.3 Gpixels/sec |
| Particle Physics | 8078.5 FPS | 1916.5 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 777 | 656 |
| DirectX 11 | 79 FPS | 44 FPS |
| DirectX 12 | 49 FPS | 26 FPS |
| GPU Compute | 4928 Ops/s | 2669 Ops/s |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 3814 | 1518 |
| Image Segmentation (HP) | 4931 | 2085 |
| Image Super Resolution (Q) | 8081 | 4847 |
| Face Detection (HP) | 8691 | 3275 |
| Pose Estimation (Q) | 33497 | 16118 |
| Text Classification (SP) | 1586 | 1440 |
| Machine Translation (HP) | 2227 | 1875 |
| Object Detection (SP) | 4384 | 1743 |
| Depth Estimation (Q) | 16173 | 6258 |
| Style Transfer (SP) | 72011 | 26368 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce GTX 1660 and 1050 TiGeneral
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | March 14, 2019 | October 25, 2016 |
| Launch price (MSRP) | $219 | $139 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Entry-level | Entry-level |
| Architecture | Turing | Pascal |
| GPU Codename | TU116 | GP107 |
| Rival Equivalent | - Radeon RX 5600 XT | - Radeon RX 570 |
| Recommended CPU | - Intel Core i5 9500 or above | - |
Desktop GPU rating (78th and 89th place)
Graphics Processing Unit
| Base Clock | 1530 MHz | 1291 MHz |
| Boost Clock | 1785 MHz | 1392 MHz |
| Shading Units | 1408 | 768 |
| Texture Mapping Units (TMUs) | 88 | 48 |
| Render Output Units (ROPs) | 48 | 32 |
| Compute Units (Pipelines) | 22 | 6 |
| Tensor Cores | No | No |
| Ray-tracing Cores | No | No |
| L1 Cache | 64KB per cluster | 48KB per cluster |
| L2 Cache | 1536KB shared | 1024KB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 86 GPixel/s | 45 GPixel/s |
| Texture Fill Rate | 157 GTexel/s | 67 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| TGP | 120 W | 75 W |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 12 nm | 14 nm |
| Die Size | 284 mm² | 132 mm² |
| Transistor Count | 6 billion | 3 billion |
| Transistor Density | 21.13 MTr/mm² | 22.73 MTr/mm² |
| Max. Temperature | - | 97°C |
Memory
| Memory Type | GDDR5 | GDDR5 |
| Memory Size | 6 GB | 4 GB |
| Memory Clock | 2001 MHz | 1752 MHz |
| Effective Memory Speed | 8000 Mbps | 7000 Mbps |
| Bus | 192-bit | 128-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 7.5 | 6.1 |
| Ray Tracing | No | No |
| DLSS | No | No |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 10