Nvidia GeForce RTX 4090 vs Nvidia GeForce RTX 4070 Ti SUPER
92
out 100
VS
72
out 100
Compared 2 processors: Nvidia GeForce RTX 4090, vs Nvidia GeForce RTX 4070 Ti SUPER. 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 | 277 199 191 154 | 207 146 140 104 |
 The Witcher 3 | 288 265 187 100 | 225 190 142 72 |
 Counter-Strike 2 | 329 244 185 91 | 292 216 165 85 |
 Far Cry 6 | 203 182 167 104 | 164 149 136 85 |
 Hogwarts Legacy | 201 164 132 76 | 143 120 96 55 |
 COD Modern Warfare 3 | 274 258 221 149 | 191 187 144 100 |
 Ghost of Tsushima | 183 154 137 91 | 130 110 96 58 |
 Cyberpunk 2077 | 227 208 143 68 | 175 151 107 48 |
 Shadow of the Tomb Raider | 304 277 215 119 | 263 247 196 104 |
| 1080p High | 254 | 199 |
| 1080p Ultra | 217 | 168 |
| 1440p Ultra | 175 | 136 |
| 4K Ultra | 106 | 79 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 36322 | 24225 |
| Solar Bay | 186930 | 116030 |
| Port Royal | 26115 | 15768 |
| Fire Strike | 72253 | 56271 |
| Night Raid | 195300 | 174807 |
| Background Blur | 318.9 frames/s | 331.7 frames/s |
| Face Detection | 222.8 frames/s | 211.6 frames/s |
| Horizon Detection | 14.2 Gpix/sec | 9.63 Gpix/sec |
| Edge Detection | 21 Gpix/sec | 13.7 Gpix/sec |
| Gaussian Blur | 23.9 Gpix/sec | 13.9 Gpix/sec |
| Feature Matching | 2.38 Gpix/sec | 2.15 Gpix/sec |
| Stereo Matching | 1950 Gpix/sec | 1210 Gpix/sec |
| Particle Physics | 48090.4 fps | 33566 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 1297 | 1218 |
| DirectX 11 | 329 fps | 280 fps |
| DirectX 12 | 150 fps | 117 fps |
| GPU Compute | 27111 Ops/s | 18522 Ops/s |
| Aztec Ruins (Normal) | 1617.6 fps | 1300.6 fps |
| Car Chase | 1228.6 fps | 1119.6 fps |
| Manhattan 3.1.1 (1440p) | 1234.6 fps | 943.4 fps |
| T-Rex | 6286 fps | 4724.8 fps |
| ALU 2 | 15073.4 fps | 8528.7 fps |
| Driver Overhead 2 | 303.7 fps | 289.1 fps |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
| Tessellation | 12119.1 | 8597.7 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Announced | September, 20, 2022 | January, 24, 2024 |
| Form Factor | PC use | PC use |
| Use case | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ada Lovelace | Ada Lovelace |
| Codename | AD102 | AD103 |
| Price | 1599 | 799 |
GPU
| GPU Frequency | 2235 MHz | 2340 MHz |
| Boost GPU Frequency | 2520 MHz | 2610 MHz |
| Shader Units | 16384 | 8448 |
| TMUs | 512 | 264 |
| ROPs | 176 | 96 |
| Execution Units | 128 | 66 |
| Ray Tracing Cores | 128 | 66 |
| Tensor Cores | 512 | 264 |
| L1 cache | 128 KB/core | 128 KB/core |
| L2 cache | 72 KB/core | 48000 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 444 Gpix/sec | 251 Gpix/sec |
| Texture Fill Rate | 1290 GTex/s | 689 GTex/s |
| FLOPS | 82.6 TFLOPS | 44.1 TFLOPS |
Process
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 450 W | 285 W |
| Process | TSMC | TSMC |
| Process tech. | 5 nm | 5 nm |
| Transistor Size | 609 mm² | 379 mm² |
| Transistor count | 76.3 billion | 45 billion |
| Transistor density | 125.29 MTr/mm² | 118.73 MTr/mm² |
Memory
| Interface | GDDR6X | GDDR6X |
| Memory Frequency | 2625 MHz | 1313 MHz |
| Bus | 384 bit | 256 bit |
| ECC support | No | No |
| Effective Memory Speed | 21000 MB/s | 21000 MB/s |
| Memory Size | 24 GB | 16 GB |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| CUDA | 8.9 | 8.9 |
| DisplayPort | 1.4a | 1.4a |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 3 |
Results
After analyzing the data, we consider Nvidia GeForce RTX 4090 the clear winner in this comparison.
Survey
Total Votes: 0
