GeForce RTX 4070 vs 3060 Ti
VS
Nvidia GeForce RTX 4070
AD104
We compared two discrete desktop gaming GPUs: the GeForce RTX 4070 12 GB with 46 pipelines and 5888 shaders against the 2 years and 4 months older RTX 3060 Ti 8 GB that utilizes 38 pipelines and 4864 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 4070
- Performs significantly better (up to 51%) in 3DMark Steel Nomad Lite
- 80% higher maximum theoretical performance (29.1 vs 16.2 TFLOPS)
- Manufactured using a more efficient 5 nm process technology
- Shows 38% higher average frame rate in modern games at QHD resolution – 106 vs 77 FPS
- Includes 4 GB more video memory
- Supports Nvidia DLSS 3 technology
- Achieves 45% more points in the GeekBench 6 Compute test (167K vs 115K)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 172 115 102 79 |
132 88 75 54 |
| The Witcher 3 | 194 159 114 61 |
152 128 92 47 |
| Counter-Strike 2 | 272 205 149 81 |
226 169 121 64 |
| Far Cry 6 | 149 133 115 68 |
114 103 83 47 |
| Hogwarts Legacy | 117 97 77 39 |
86 73 55 29 |
| CoD: Modern Warfare III | 149 145 107 69 |
107 99 72 47 |
| Ghost of Tsushima | 106 88 72 43 |
82 69 48 28 |
| Cyberpunk 2077 | 129 119 75 37 |
92 81 48 22 |
| Shadow of the Tomb Raider | 211 190 145 80 |
139 132 95 53 |
| 1080p High | 167 | 126 |
| 1080p Ultra | 139 | 105 |
| 1440p Ultra | 106 | 77 |
| 4K Ultra | 62 | 43 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 17799 | 11707 |
| Solar Bay | 82861 | 54429 |
| Port Royal | 11156 | 6971 |
| Fire Strike | 44067 | 29571 |
| Wild Life Extreme | 35472 | 24417 |
| Night Raid | 153385 | 109862 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 233 img/sec | 185.1 img/sec |
| Face Detection | 141.7 img/sec | 108.4 img/sec |
| Horizon Detection | 6.62 Gpixels/sec | 5.35 Gpixels/sec |
| Edge Detection | 9.19 Gpixels/sec | 7.17 Gpixels/sec |
| Gaussian Blur | 9.2 Gpixels/sec | 5.54 Gpixels/sec |
| Feature Matching | 1.78 Gpixels/sec | 1.15 Gpixels/sec |
| Stereo Matching | 845.4 Gpixels/sec | 478 Gpixels/sec |
| Particle Physics | 25043.9 FPS | 15183 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1165 | 989 |
| DirectX 11 | 243 FPS | 164 FPS |
| DirectX 12 | 103 FPS | 78 FPS |
| GPU Compute | 14570 Ops/s | 9865 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 4070
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-14 (kashitsu) | Cinebench 2024 | 18051 |
GeForce RTX 3060 Ti
No benchmark results yet
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) | 10246 | 7384 |
| Image Segmentation (HP) | 26153 | 19320 |
| Image Super Resolution (Q) | 32054 | 16108 |
| Face Detection (HP) | 51337 | 34615 |
| Pose Estimation (Q) | 124617 | 74811 |
| Text Classification (SP) | 3703 | 2638 |
| Machine Translation (HP) | 5484 | 4136 |
| Object Detection (SP) | 13134 | 8718 |
| Depth Estimation (Q) | 50548 | 25946 |
| Style Transfer (SP) | 263477 | 153275 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 4070 and 3060 TiGeneral
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | April 13, 2023 | December 2, 2020 |
| Launch price (MSRP) | $599 | $399 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ada Lovelace | Ampere |
| GPU Codename | AD104 | GA104 |
| Rival Equivalent | - Radeon RX 7900 XT | - Radeon RX 6700 XT |
| Successor | - GeForce RTX 5070 | - GeForce RTX 5060 Ti (8GB) |
| Recommended CPU | - Intel Core i7 14700K or above | - Intel Core i5 12600K or above |
Desktop GPU rating (28th and 48th place)
Graphics Processing Unit
| Base Clock | 1920 MHz | 1410 MHz |
| Boost Clock | 2475 MHz | 1665 MHz |
| Shading Units | 5888 | 4864 |
| Texture Mapping Units (TMUs) | 184 | 152 |
| Render Output Units (ROPs) | 64 | 80 |
| Compute Units (Pipelines) | 46 | 38 |
| Tensor Cores | 184 | 152 |
| Ray-tracing Cores | 46 | 38 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 36MB shared | 4MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 158 GPixel/s | 133 GPixel/s |
| Texture Fill Rate | 455 GTexel/s | 253 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 200 W | 200 W |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 5 nm | 8 nm |
| Die Size | 294 mm² | 392 mm² |
| Transistor Count | 35 billion | 17 billion |
| Transistor Density | 119.05 MTr/mm² | 43.37 MTr/mm² |
Memory
| Memory Type | GDDR6X | GDDR6 |
| Memory Size | 12 GB | 8 GB |
| Memory Clock | 1313 MHz | 1750 MHz |
| Effective Memory Speed | 21000 Mbps | 14000 Mbps |
| Bus | 192-bit | 256-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 | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 2 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 44
