Nvidia GeForce RTX 3050 vs AMD Radeon 660M
26
out 100
VS
24
out 100
Compared 2 processors: Nvidia GeForce RTX 3050, vs AMD Radeon 660M. Below are specs, tests, pros and cons for each device
Review
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
Tests & specs
Specs & test comparisonGames
| Game title | 1080p (High) 1080p (Ultra) 1440p (Ultra) 4K (Ultra) | |
 Forza Horizon 5 | 92 53 45 27 | 27 13 11 n/a |
 The Witcher 3 | 89 73 51 28 | 10 12 n/a n/a |
 Counter-Strike 2 | 143 100 71 34 | 24 18 12 n/a |
 Far Cry 6 | 75 66 51 25 | 22 18 10 n/a |
 Hogwarts Legacy | 49 40 29 14 | 12 n/a n/a n/a |
 COD Modern Warfare 3 | 59 50 35 23 | 20 16 13 n/a |
 Ghost of Tsushima | 47 34 25 13 | 12 9 n/a n/a |
 Cyberpunk 2077 | 49 45 26 10 | 9 10 n/a n/a |
 Shadow of the Tomb Raider | 82 73 52 25 | 15 14 11 n/a |
| 1080p High | 76 | 17 |
| 1080p Ultra | 59 | 13 |
| 1440p Ultra | 43 | 9 |
| 4K Ultra | 22 | - |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 6227 | 1532 |
| Solar Bay | 30015 | 6227 |
| Port Royal | 3542 | 613 |
| Fire Strike | 15972 | 4906 |
| Night Raid | 74372 | 20196 |
| Background Blur | 110.4 frames/s | 36 frames/s |
| Face Detection | 64.4 frames/s | 16.4 frames/s |
| Horizon Detection | 2.87 Gpix/sec | 0.48 Gpix/sec |
| Edge Detection | 3.76 Gpix/sec | 0.65 Gpix/sec |
| Gaussian Blur | 2.89 Gpix/sec | 0.53 Gpix/sec |
| Feature Matching | 0.81 Gpix/sec | 0.18 Gpix/sec |
| Stereo Matching | 270.9 Gpix/sec | 46.5 Gpix/sec |
| Particle Physics | 9339.7 fps | 2056.5 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 918 | 701 |
| DirectX 11 | 91 fps | 92 fps |
| DirectX 12 | 59 fps | 45 fps |
| GPU Compute | 6528 Ops/s | 1972 Ops/s |
| Aztec Ruins (Normal) | 393.8 fps | 109.1 fps |
| Car Chase | 361.9 fps | 106.4 fps |
| Manhattan 3.1.1 (1440p) | 294.2 fps | 87.7 fps |
| T-Rex | 1381.8 fps | 368.5 fps |
| ALU 2 | 1974.1 fps | 451.3 fps |
| Driver Overhead 2 | 286.3 fps | 170.1 fps |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
| Tessellation | 2081.3 | 320.9 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | AMD |
| Build | Discrete | Integrated |
| Announced | January, 27, 2022 | January, 1, 2022 |
| Form Factor | PC use | Laptop use |
| Use case | Gaming | Universal |
| Segment | Entry-level | Entry-level |
| Architecture | Ampere | RDNA 2.0 |
| Codename | GA106 | Rembrandt |
| Price | 249 | n/a |
GPU
| GPU Frequency | 1552 MHz | 400 MHz |
| Boost GPU Frequency | 1777 MHz | 1800-1900 MHz |
| Shader Units | 2560 | 384 |
| TMUs | 80 | 24 |
| ROPs | 32 | 16 |
| Execution Units | 20 | 6 |
| Ray Tracing Cores | 20 | 6 |
| Tensor Cores | 80 | n/a |
| L1 cache | 128 KB/core | 128 KB/core |
| L2 cache | 2000 KB/core | 1024 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 57 Gpix/sec | 29-30 Gpix/sec |
| Texture Fill Rate | 142 GTex/s | 43-46 GTex/s |
| FLOPS | 9.1 TFLOPS | 1.4-1.5 TFLOPS |
Process
| Interface | PCIe 4.0 x8 | PCIe 4.0 x8 |
| TGP | 130 W | 15 W |
| Process | Samsung | TSMC |
| Process tech. | 8 nm | 6 nm |
| Transistor Size | 276 mm² | 208 mm² |
| Transistor count | 12 billion | 13.1 billion |
| Transistor density | 43.48 MTr/mm² | 62.98 MTr/mm² |
Memory
| Interface | GDDR6 | System Shared |
| Memory Frequency | 1750 MHz | n/a |
| Bus | 128 bit | n/a |
| ECC support | No | No |
| Effective Memory Speed | 14000 MB/s | n/a |
| Memory Size | 8 GB | n/a |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.2 |
| OpenGL | 4.6 | 4.6 |
| CUDA | 8.6 | n/a |
| DisplayPort | 1.4a | n/a |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 2 | No |
Results
No clear favorite identified yet; updates may follow as new data arrives.
Survey
Total Votes: 0
