AMD Radeon RX 570 vs GeForce GTX 1650
AMD Radeon RX 570
Polaris 20
Nvidia GeForce GTX 1650
TU117
We compared two discrete desktop gaming GPUs: the Radeon RX 570 with 2048 shaders against the 2 years newer GeForce 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 Radeon RX 570
- 70% higher maximum theoretical performance (5.1 vs 3 TFLOPS)
- Has 75% higher memory bandwidth: 224 vs 128.1 GB/s
- Has 2.3x more shading units (2048 vs 896)
Reasons to consider the GeForce GTX 1650
- Manufactured using a more efficient 12 nm process technology
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 67 34 28 15 |
57 32 24 15 |
| The Witcher 3 | 42 37 19 12 |
43 33 21 10 |
| Counter-Strike 2 | 64 45 29 13 |
75 54 34 14 |
| Far Cry 6 | 49 41 30 15 |
45 41 26 13 |
| Hogwarts Legacy | 29 23 15 - |
25 21 17 - |
| CoD: Modern Warfare III | 42 35 25 13 |
37 31 20 14 |
| Ghost of Tsushima | 29 19 13 9 |
25 15 14 - |
| Cyberpunk 2077 | 28 24 14 - |
28 22 13 - |
| Shadow of the Tomb Raider | 50 45 26 13 |
45 43 29 13 |
| 1080p High | 44 | 42 |
| 1080p Ultra | 34 | 32 |
| 1440p Ultra | 22 | 22 |
| 4K Ultra | 12 | 11 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 3855 | 3562 |
| Solar Bay | - | 12275 |
| Fire Strike | 13443 | 9702 |
| Wild Life Extreme | 7938 | 7353 |
| Night Raid | 50382 | 46224 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 55.7 img/sec | 66.4 img/sec |
| Face Detection | 31.3 img/sec | 43.3 img/sec |
| Horizon Detection | 1.41 Gpixels/sec | 1.51 Gpixels/sec |
| Edge Detection | 2.82 Gpixels/sec | 1.68 Gpixels/sec |
| Gaussian Blur | 2.57 Gpixels/sec | 1.87 Gpixels/sec |
| Feature Matching | 0.31 Gpixels/sec | 0.49 Gpixels/sec |
| Stereo Matching | 143.2 Gpixels/sec | 187.9 Gpixels/sec |
| Particle Physics | 5080.1 FPS | 5261.5 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 725 | 551 |
| DirectX 11 | 55 FPS | 58 FPS |
| DirectX 12 | 39 FPS | 35 FPS |
| GPU Compute | 2869 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) | 2676 | 3208 |
| Image Segmentation (HP) | 3757 | 4254 |
| Image Super Resolution (Q) | 6179 | 7050 |
| Face Detection (HP) | 10752 | 6849 |
| Pose Estimation (Q) | 35488 | 23562 |
| Text Classification (SP) | 1051 | 1755 |
| Machine Translation (HP) | 1933 | 3096 |
| Object Detection (SP) | 3048 | 3710 |
| Depth Estimation (Q) | 12040 | 12946 |
| Style Transfer (SP) | 71201 | 48894 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 570 and GeForce GTX 1650General
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | April 18, 2017 | April 23, 2019 |
| Launch price (MSRP) | $169 | $149 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Entry-level |
| Architecture | GCN 4.0 | Turing |
| GPU Codename | Polaris 20 | TU117 |
| Rival Equivalent | - GeForce GTX 1050 Ti | - |
| Recommended CPU | - Intel Core i5 8500 or above | - Intel Core i5 9400 or above |
Desktop GPU rating (85th and 88th place)
Graphics Processing Unit
| Base Clock | 1168 MHz | 1485 MHz |
| Boost Clock | 1244 MHz | 1665 MHz |
| Shading Units | 2048 | 896 |
| Texture Mapping Units (TMUs) | 128 | 56 |
| Render Output Units (ROPs) | 32 | 32 |
| Compute Units (Pipelines) | - | 14 |
| Tensor Cores | No | No |
| Ray-tracing Cores | No | No |
| L1 Cache | 16KB per cluster | 64KB per cluster |
| L2 Cache | 2MB shared | 1024KB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 40 GPixel/s | 53 GPixel/s |
| Texture Fill Rate | 159 GTexel/s | 93 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| TGP | 150 W | 75 W |
| Manufacturing | GlobalFoundries | TSMC |
| Fabrication Process | 14 nm | 12 nm |
| Die Size | 232 mm² | 200 mm² |
| Transistor Count | 5 billion | 4 billion |
| Transistor Density | 21.55 MTr/mm² | 20 MTr/mm² |
Memory
| Memory Type | GDDR5 | GDDR5 |
| Memory Size | 4 GB | 4 GB |
| Memory Clock | 1750 MHz | 2001 MHz |
| Effective Memory Speed | 7000 Mbps | 8000 Mbps |
| Bus | 256-bit | 128-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| CUDA | - | 7.5 |
| Ray Tracing | No | No |
| DLSS | No | No |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 52