GeForce RTX 4090 vs 4070 Ti
VS
Nvidia GeForce RTX 4090
AD102
We compared two discrete desktop gaming GPUs: the GeForce RTX 4090 24 GB with 128 pipelines and 16384 shaders against the 4 months newer RTX 4070 Ti 12 GB that utilizes 60 pipelines and 7680 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
DeviceFacts Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 4090
- Performs significantly better (up to 79%) in 3DMark Steel Nomad Lite
- 2.1x higher maximum theoretical performance (82.6 vs 40.1 TFLOPS)
- Shows 38% higher average frame rate in modern games at QHD resolution – 177 vs 128 FPS
- Includes 12 GB more video memory
- Features 272 more tensor cores for effective ML and AI workloads
- Has 2x higher memory bandwidth: 1010 vs 504 GB/s
- Achieves 44% more points in the GeekBench 6 Compute test (316K vs 219K)
- Has 2.1x more shading units (16384 vs 7680)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 275 199 193 155 |
197 136 126 100 |
| The Witcher 3 | 292 268 191 101 |
211 190 135 72 |
| Counter-Strike 2 | 339 238 188 90 |
288 218 160 83 |
| Far Cry 6 | 203 179 170 104 |
164 147 130 81 |
| Hogwarts Legacy | 200 163 132 74 |
140 115 89 50 |
| CoD: Modern Warfare III | 266 263 219 151 |
181 172 134 90 |
| Ghost of Tsushima | 188 152 137 91 |
124 107 92 55 |
| Cyberpunk 2077 | 226 208 143 66 |
161 147 98 44 |
| Shadow of the Tomb Raider | 302 284 222 118 |
257 243 188 98 |
| 1080p High | 255 | 191 |
| 1080p Ultra | 217 | 164 |
| 1440p Ultra | 177 | 128 |
| 4K Ultra | 106 | 75 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 36299 | 22743 |
| Solar Bay | 187525 | 108437 |
| Port Royal | 26127 | 13995 |
| Fire Strike | 72432 | 53473 |
| Wild Life Extreme | 85218 | 45396 |
| Night Raid | 195813 | 171208 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 318.9 img/sec | 371.2 img/sec |
| Face Detection | 222.8 img/sec | 235 img/sec |
| Horizon Detection | 14.2 Gpixels/sec | 7.51 Gpixels/sec |
| Edge Detection | 21 Gpixels/sec | 10.6 Gpixels/sec |
| Gaussian Blur | 23.9 Gpixels/sec | 12.4 Gpixels/sec |
| Feature Matching | 2.38 Gpixels/sec | 2.03 Gpixels/sec |
| Stereo Matching | 1950 Gpixels/sec | 1120 Gpixels/sec |
| Particle Physics | 48090.4 FPS | 30420.2 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1303 | 1209 |
| DirectX 11 | 323 FPS | 287 FPS |
| DirectX 12 | 151 FPS | 115 FPS |
| GPU Compute | 25991 Ops/s | 18136 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 4090
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-10-06 (Devansh) | Geekbench 6 OpenCL | 394674 |
| 📘 2026-10-06 (Devansh) | Geekbench 7 OpenCL | 338129 |
| 📘 2026-04-03 (afroman420IU) | Cinebench 2024 | 32578 |
GeForce RTX 4070 Ti
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-09-14 (Isa) | Cinebench 2024 | 80717 |
| 📘 2026-06-02 (Harley) | Cinebench 2024 | 79993 |
| 📘 2026-03-27 (minato) | Cinebench 2024 | 80470 |
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) | 15600 | 12496 |
| Image Segmentation (HP) | 36657 | 33378 |
| Image Super Resolution (Q) | 48114 | 37180 |
| Face Detection (HP) | 78111 | 62919 |
| Pose Estimation (Q) | 289639 | 171125 |
| Text Classification (SP) | 4074 | 3630 |
| Machine Translation (HP) | 6349 | 6420 |
| Object Detection (SP) | 21186 | 15804 |
| Depth Estimation (Q) | 75599 | 58647 |
| Style Transfer (SP) | 601428 | 331379 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 4090 and 4070 TiGeneral
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | September 20, 2022 | January 3, 2023 |
| Launch price (MSRP) | $1599 | $799 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | Ada Lovelace | Ada Lovelace |
| GPU Codename | AD102 | AD104 |
| Rival Equivalent | - | - Radeon RX 7900 XT |
| Successor | - GeForce RTX 5090 | - GeForce RTX 5070 Ti |
| Recommended CPU | - Intel Core i9 14900K or above | - Intel Core i7 14700K or above |
Desktop GPU rating (3rd and 15th place)
Graphics Processing Unit
| Base Clock | 2235 MHz | 2310 MHz |
| Boost Clock | 2520 MHz | 2610 MHz |
| Shading Units | 16384 | 7680 |
| Texture Mapping Units (TMUs) | 512 | 240 |
| Render Output Units (ROPs) | 176 | 80 |
| Compute Units (Pipelines) | 128 | 60 |
| Tensor Cores | 512 | 240 |
| Ray-tracing Cores | 128 | 60 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 72MB shared | 48MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 444 GPixel/s | 209 GPixel/s |
| Texture Fill Rate | 1290 GTexel/s | 626 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 450 W | 285 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 5 nm |
| Die Size | 609 mm² | 294 mm² |
| Transistor Count | 76.3 billion | 35 billion |
| Transistor Density | 125.29 MTr/mm² | 119.05 MTr/mm² |
Memory
| Memory Type | GDDR6X | GDDR6X |
| Memory Size | 24 GB | 12 GB |
| Memory Clock | 2625 MHz | 1313 MHz |
| Effective Memory Speed | 21000 Mbps | 21000 Mbps |
| Bus | 384-bit | 192-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 8.9 | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 3 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 6