GeForce RTX 5070 Ti vs RTX 4090
VS
Nvidia GeForce RTX 5070 Ti
GB203-200-A1
Nvidia GeForce RTX 4090
AD102
We compared two discrete desktop gaming GPUs: the GeForce RTX 5070 Ti 16 GB with 70 pipelines and 8960 shaders against the 2 years and 4 months older RTX RTX 4090 24 GB that utilizes 128 pipelines and 16384 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 RTX 5070 Ti
- Manufactured using a more efficient 4 nm process technology
- Supports Nvidia DLSS 4 technology
Reasons to consider the GeForce RTX 4090
- Performs significantly better (up to 41%) in 3DMark Steel Nomad Lite
- 88% higher maximum theoretical performance (82.6 vs 43.9 TFLOPS)
- Shows 20% higher average frame rate in modern games at QHD resolution – 177 vs 148 FPS
- Includes 8 GB more video memory
- Features 232 more tensor cores for effective ML and AI workloads
- Achieves 32% more points in the GeekBench 6 Compute test (316K vs 240K)
- Has 83% more shading units (16384 vs 8960)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 229 164 155 121 |
275 199 193 155 |
| The Witcher 3 | 244 215 155 83 |
292 268 191 101 |
| Counter-Strike 2 | 298 221 172 86 |
339 238 188 90 |
| Far Cry 6 | 178 158 146 89 |
203 179 170 104 |
| Hogwarts Legacy | 160 131 107 58 |
200 163 132 74 |
| CoD: Modern Warfare III | 212 211 163 115 |
266 263 219 151 |
| Ghost of Tsushima | 144 122 109 70 |
188 152 137 91 |
| Cyberpunk 2077 | 193 176 122 55 |
226 208 143 66 |
| Shadow of the Tomb Raider | 279 265 207 106 |
302 284 222 118 |
| 1080p High | 215 | 255 |
| 1080p Ultra | 185 | 217 |
| 1440p Ultra | 148 | 177 |
| 4K Ultra | 87 | 106 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 27839 | 36299 |
| Solar Bay | 137852 | 187525 |
| Port Royal | 19713 | 26127 |
| Fire Strike | 67490 | 72432 |
| Wild Life Extreme | 58033 | 85218 |
| Night Raid | 188802 | 195813 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 297.9 img/sec | 318.9 img/sec |
| Face Detection | 218.6 img/sec | 222.8 img/sec |
| Horizon Detection | 10.1 Gpixels/sec | 14.2 Gpixels/sec |
| Edge Detection | 13.9 Gpixels/sec | 21 Gpixels/sec |
| Gaussian Blur | 14.8 Gpixels/sec | 23.9 Gpixels/sec |
| Feature Matching | 2.03 Gpixels/sec | 2.38 Gpixels/sec |
| Stereo Matching | 1290 Gpixels/sec | 1950 Gpixels/sec |
| Particle Physics | 35438.3 FPS | 48090.4 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1323 | 1303 |
| DirectX 11 | 303 FPS | 323 FPS |
| DirectX 12 | 126 FPS | 151 FPS |
| GPU Compute | 17781 Ops/s | 25991 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 5070 Ti
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-08-28 (NOX) | Cinebench 2024 | 88980 |
GeForce RTX 4090
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-04-03 (afroman420IU) | Cinebench 2024 | 32578 |
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) | 14913 | 15600 |
| Image Segmentation (HP) | 45199 | 36657 |
| Image Super Resolution (Q) | 39360 | 48114 |
| Face Detection (HP) | 84188 | 78111 |
| Pose Estimation (Q) | 161400 | 289639 |
| Text Classification (SP) | 4010 | 4074 |
| Machine Translation (HP) | 7973 | 6349 |
| Object Detection (SP) | 18934 | 21186 |
| Depth Estimation (Q) | 67761 | 75599 |
| Style Transfer (SP) | 335879 | 601428 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 5070 Ti and RTX 4090General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 7, 2025 | September 20, 2022 |
| Launch price (MSRP) | $749 | $1599 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | High-end |
| Architecture | Blackwell 2.0 | Ada Lovelace |
| GPU Codename | GB203-200-A1 | AD102 |
| Rival Equivalent | - Radeon RX 9070 XT | - |
| Successor | - | - GeForce RTX 5090 |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - Intel Core i9 14900K or above |
Desktop GPU rating (8th and 3rd place)
Graphics Processing Unit
| Base Clock | 2295 MHz | 2235 MHz |
| Boost Clock | 2452 MHz | 2520 MHz |
| Shading Units | 8960 | 16384 |
| Texture Mapping Units (TMUs) | 280 | 512 |
| Render Output Units (ROPs) | 96 | 176 |
| Compute Units (Pipelines) | 70 | 128 |
| Tensor Cores | 280 | 512 |
| Ray-tracing Cores | 70 | 128 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 48MB shared | 72MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 235 GPixel/s | 444 GPixel/s |
| Texture Fill Rate | 687 GTexel/s | 1290 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| TGP | 300 W | 450 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 5 nm |
| Die Size | 378 mm² | 609 mm² |
| Transistor Count | 45.6 billion | 76.3 billion |
| Transistor Density | 120.63 MTr/mm² | 125.29 MTr/mm² |
Memory
| Memory Type | GDDR7 | GDDR6X |
| Memory Size | 16 GB | 24 GB |
| Memory Clock | 1750 MHz | 2625 MHz |
| Effective Memory Speed | 28000 Mbps | 21000 Mbps |
| Bus | 256-bit | 384-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12.2 | 12 |
| Vulkan | 1.4 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 12.0 | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 4 | DLSS 3 |
| DisplayPort | 2.1b | 1.4a |
Cast your vote
Total votes: 120