GeForce GTX 1650 SUPER vs GTX 1650
Nvidia GeForce GTX 1650
TU117
We compared two discrete desktop gaming GPUs: the GeForce GTX 1650 SUPER with 20 pipelines and 1280 shaders against the GTX 1650 that utilizes 14 pipelines and 896 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 1650 SUPER
- Performs better (up to 28%) in 3DMark Steel Nomad Lite
- Shows 41% higher average frame rate in modern games at QHD resolution – 31 vs 22 FPS
- 47% higher maximum theoretical performance (4.4 vs 3 TFLOPS)
- Has 50% higher memory bandwidth: 192 vs 128.1 GB/s
- Achieves 46% more points in the GeekBench 6 Compute test (57K vs 39K)
- Has 43% more shading units (1280 vs 896)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 73 42 33 21 |
57 32 24 15 |
| The Witcher 3 | 60 46 32 16 |
43 33 21 10 |
| Counter-Strike 2 | 107 71 49 21 |
75 54 34 14 |
| Far Cry 6 | 57 48 37 19 |
45 41 26 13 |
| Hogwarts Legacy | 33 26 22 11 |
25 21 17 - |
| CoD: Modern Warfare III | 41 35 24 15 |
37 31 20 14 |
| Ghost of Tsushima | 32 22 20 - |
25 15 14 - |
| Cyberpunk 2077 | 36 33 20 - |
28 22 13 - |
| Shadow of the Tomb Raider | 62 55 38 17 |
45 43 29 13 |
| 1080p High | 56 | 42 |
| 1080p Ultra | 42 | 32 |
| 1440p Ultra | 31 | 22 |
| 4K Ultra | 15 | 11 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 4691 | 3562 |
| Solar Bay | - | 12275 |
| Fire Strike | 12267 | 9702 |
| Wild Life Extreme | 9634 | 7353 |
| Night Raid | 60033 | 46224 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 106.6 img/sec | 66.4 img/sec |
| Face Detection | 58.3 img/sec | 43.3 img/sec |
| Horizon Detection | 1.98 Gpixels/sec | 1.51 Gpixels/sec |
| Edge Detection | 2.67 Gpixels/sec | 1.68 Gpixels/sec |
| Gaussian Blur | 2.79 Gpixels/sec | 1.87 Gpixels/sec |
| Feature Matching | 0.75 Gpixels/sec | 0.49 Gpixels/sec |
| Stereo Matching | 248.2 Gpixels/sec | 187.9 Gpixels/sec |
| Particle Physics | 7783.2 FPS | 5261.5 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 749 | 551 |
| DirectX 11 | 73 FPS | 58 FPS |
| DirectX 12 | 45 FPS | 35 FPS |
| GPU Compute | 4455 Ops/s | 3031 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) | 3533 | 3208 |
| Image Segmentation (HP) | 5144 | 4254 |
| Image Super Resolution (Q) | 7927 | 7050 |
| Face Detection (HP) | 8860 | 6849 |
| Pose Estimation (Q) | 30433 | 23562 |
| Text Classification (SP) | 1622 | 1755 |
| Machine Translation (HP) | 2754 | 3096 |
| Object Detection (SP) | 4278 | 3710 |
| Depth Estimation (Q) | 15240 | 12946 |
| Style Transfer (SP) | 66527 | 48894 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce GTX 1650 SUPER and GTX 1650General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | April 23, 2019 | April 23, 2019 |
| Launch price (MSRP) | $159 | $149 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Entry-level | Entry-level |
| Architecture | Turing | Turing |
| GPU Codename | TU116 | TU117 |
| Rival Equivalent | - Radeon RX 5500 XT | - |
| Recommended CPU | - Intel Core i5 9400 or above | - Intel Core i5 9400 or above |
Desktop GPU rating (81st and 88th place)
Graphics Processing Unit
| Base Clock | 1530 MHz | 1485 MHz |
| Boost Clock | 1725 MHz | 1665 MHz |
| Shading Units | 1280 | 896 |
| Texture Mapping Units (TMUs) | 80 | 56 |
| Render Output Units (ROPs) | 32 | 32 |
| Compute Units (Pipelines) | 20 | 14 |
| Tensor Cores | No | No |
| Ray-tracing Cores | No | No |
| L1 Cache | 64KB per cluster | 64KB per cluster |
| L2 Cache | 1024KB shared | 1024KB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 55 GPixel/s | 53 GPixel/s |
| Texture Fill Rate | 138 GTexel/s | 93 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| TGP | 100 W | 75 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 12 nm | 12 nm |
| Die Size | 284 mm² | 200 mm² |
| Transistor Count | 6 billion | 4 billion |
| Transistor Density | 21.13 MTr/mm² | 20 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR5 |
| Memory Size | 4 GB | 4 GB |
| Memory Clock | 2000 MHz | 2001 MHz |
| Effective Memory Speed | 12000 Mbps | 8000 Mbps |
| Bus | 128-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 | 7.5 |
| Ray Tracing | No | No |
| DLSS | No | No |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 29