Nvidia GeForce RTX 5060 Ti (8GB) vs Nvidia GeForce RTX 5090
46
out 100
VS
97
out 100
Compared 2 processors: Nvidia GeForce RTX 5060 Ti (8GB), vs Nvidia GeForce RTX 5090. 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 | 161 104 94 72 | 332 242 231 183 |
 The Witcher 3 | 177 152 109 59 | 366 338 234 127 |
 Counter-Strike 2 | 266 199 143 82 | 379 271 209 98 |
 Far Cry 6 | 137 127 108 67 | 235 202 198 124 |
 Hogwarts Legacy | 109 91 69 39 | 244 210 167 96 |
 COD Modern Warfare 3 | 139 130 96 63 | 337 333 269 184 |
 Ghost of Tsushima | 96 82 63 37 | 221 190 170 114 |
 Cyberpunk 2077 | 121 106 68 30 | 259 231 166 77 |
 Shadow of the Tomb Raider | 186 176 130 70 | 334 306 238 128 |
| 1080p High | 155 | 301 |
| 1080p Ultra | 130 | 258 |
| 1440p Ultra | 98 | 209 |
| 4K Ultra | 58 | 126 |
| Deviation | High | Low |
Benchmarks
| Time Spy | 15883 | 47515 |
| Solar Bay | 75679 | 213229 |
| Port Royal | 10187 | 37529 |
| Fire Strike | 42670 | 90200 |
| Night Raid | 147785 | 209016 |
| Background Blur | n/a | 333 frames/s |
| Face Detection | n/a | 298.5 frames/s |
| Horizon Detection | n/a | 21.7 Gpix/sec |
| Edge Detection | n/a | 33.7 Gpix/sec |
| Gaussian Blur | n/a | 34.5 Gpix/sec |
| Feature Matching | n/a | 2.53 Gpix/sec |
| Stereo Matching | n/a | 2850 Gpix/sec |
| Particle Physics | n/a | 59146.9 fps |
| API | n/a | OpenCL |
| G2D Mark | 1200 | 1444 |
| DirectX 11 | 217 fps | 344 fps |
| DirectX 12 | 86 fps | 195 fps |
| GPU Compute | 12135 Ops/s | 28243 Ops/s |
| Aztec Ruins (Normal) | n/a | 1397.2 fps |
| Car Chase | n/a | 1150.3 fps |
| Manhattan 3.1.1 (1440p) | n/a | 1178.2 fps |
| T-Rex | n/a | 4812.3 fps |
| ALU 2 | n/a | 5992.8 fps |
| Driver Overhead 2 | n/a | 269.7 fps |
| API | n/a | OpenGL |
| OS | n/a | Windows |
| Tessellation | n/a | 5991.7 |
Blender
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Announced | April, 15, 2025 | January, 7, 2025 |
| Form Factor | PC use | PC use |
| Use case | Gaming | Gaming |
| Segment | Mid-range | High-end |
| Architecture | Blackwell 2.0 | Blackwell 2.0 |
| Codename | GB206-300 | GB202-300-A1 |
| Price | n/a | 1999 |
GPU
| GPU Frequency | 2407 MHz | 2017 MHz |
| Boost GPU Frequency | 2572 MHz | 2407 MHz |
| Shader Units | 4608 | 21760 |
| TMUs | 144 | 680 |
| ROPs | 48 | 176 |
| Execution Units | 36 | 170 |
| Ray Tracing Cores | 36 | 170 |
| Tensor Cores | 144 | 680 |
| L1 cache | 128 KB/core | 128 KB/core |
| L2 cache | 32000 KB/core | 88 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 123 Gpix/sec | 424 Gpix/sec |
| Texture Fill Rate | 370 GTex/s | 1637 GTex/s |
| FLOPS | 23.7 TFLOPS | 104.8 TFLOPS |
Process
| Interface | PCIe 5.0 x8 | PCIe 5.0 x16 |
| TGP | 180 W | 575 W |
| Process | TSMC | TSMC |
| Process tech. | 5 nm | 4 nm |
| Transistor Size | 263 mm² | 750 mm² |
| Transistor count | 31.1 billion | 92.2 billion |
| Transistor density | 118.25 MTr/mm² | 122.93 MTr/mm² |
Memory
| Interface | GDDR7 | GDDR7 |
| Memory Frequency | 1750 MHz | 1750 MHz |
| Bus | 128 bit | 512 bit |
| ECC support | No | No |
| Effective Memory Speed | 28000 MB/s | 28000 MB/s |
| Memory Size | 8 GB | 32 GB |
Max Throughput
API
| DirectX | 12.2 | 12 |
| Vulkan | 1.4 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| CUDA | 12.0 | 10.1 |
| DisplayPort | 2.1b | 2.1a |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 4 | DLSS 4 |
Results
After analyzing the data, we consider Nvidia GeForce RTX 5090 the clear winner in this comparison.
Survey
Total Votes: 0
