GeForce RTX 4060 Ti 16GB vs 2070 SUPER
VS
We compared two discrete desktop gaming GPUs: the GeForce RTX 4060 Ti 16GB 16 GB with 34 pipelines and 4352 shaders against the 4 years and 1 month older RTX 2070 SUPER 8 GB that utilizes 40 pipelines and 2560 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
Scores marked with a red asterisk (**) represent initial estimates from early testing.
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 4060 Ti 16GB
- Performs better (up to 35%) in 3DMark Steel Nomad Lite
- 2.4x higher maximum theoretical performance (22.1 vs 9.1 TFLOPS)
- Manufactured using a more efficient 5 nm process technology
- Shows 30% higher average frame rate in modern games at QHD resolution – 86 vs 66 FPS
- Includes 8 GB more video memory
- Supports Nvidia DLSS 3 technology
- Achieves 29% more points in the GeekBench 6 Compute test (135K vs 105K)
- Has 70% more shading units (4352 vs 2560)
Reasons to consider the GeForce RTX 2070 SUPER
- Features 184 more tensor cores for effective ML and AI workloads
- Has 56% higher memory bandwidth: 448 vs 288 GB/s
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 144 94 83 62 |
123 74 65 44 |
| The Witcher 3 | 172 141 99 53 |
136 113 79 43 |
| Counter-Strike 2 | 245 190 132 76 |
202 146 107 56 |
| Far Cry 6 | 129 117 92 56 |
103 91 73 40 |
| Hogwarts Legacy | 95 81 62 32 |
74 61 46 25 |
| CoD: Modern Warfare III | 118 112 81 52 |
93 86 59 41 |
| Ghost of Tsushima | 88 75 57 31 |
73 58 41 26 |
| Cyberpunk 2077 | 105 92 56 26 |
82 72 43 22 |
| Shadow of the Tomb Raider | 161 147 111 59 |
121 114 80 41 |
| 1080p High | 140 | 112 |
| 1080p Ultra | 117 | 91 |
| 1440p Ultra | 86 | 66 |
| 4K Ultra | 50 | 38 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 13456 | 10166 |
| Solar Bay | 62446 | 45863 |
| Port Royal | 8119 | 6032 |
| Fire Strike | 34258 | 25679 |
| Wild Life Extreme | 25587 | 20744 |
| Night Raid | 135657 | 102662 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 232.6 img/sec | 166.7 img/sec |
| Face Detection | 138.4 img/sec | 103.3 img/sec |
| Horizon Detection | 4.68 Gpixels/sec | 4.21 Gpixels/sec |
| Edge Detection | 6.06 Gpixels/sec | 5.56 Gpixels/sec |
| Gaussian Blur | 6.99 Gpixels/sec | 5.58 Gpixels/sec |
| Feature Matching | 1.6 Gpixels/sec | 1.17 Gpixels/sec |
| Stereo Matching | 652.6 Gpixels/sec | 489.7 Gpixels/sec |
| Particle Physics | 19534.7 FPS | 13242.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1078 | 878 |
| DirectX 11 | 199 FPS | 154 FPS |
| DirectX 12 | 89 FPS | 67 FPS |
| GPU Compute | 11953 Ops/s | 7441 Ops/s |
Blender
Blender GPU
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) | - | 6648 |
| Image Segmentation (HP) | - | 16442 |
| Image Super Resolution (Q) | - | 15383 |
| Face Detection (HP) | - | 32861 |
| Pose Estimation (Q) | - | 66348 |
| Text Classification (SP) | - | 2166 |
| Machine Translation (HP) | - | 4239 |
| Object Detection (SP) | - | 8194 |
| Depth Estimation (Q) | - | 26192 |
| Style Transfer (SP) | - | 137642 |
| Framework | - | ONNX |
| Backend | - | DirectML |
Specifications
Technical specifications of GeForce RTX 4060 Ti 16GB and 2070 SUPERGeneral
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | July 18, 2023 | July 9, 2019 |
| Launch price (MSRP) | $499 | $499 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ada Lovelace | Turing |
| GPU Codename | AD106 | TU104 |
| Successor | - GeForce RTX 5060 Ti (16GB) | - |
| Recommended CPU | - Intel Core i5 14600K or above | - Intel Core i7 9700K or above |
Desktop GPU rating (40th and 57th place)
Graphics Processing Unit
| Base Clock | 2310 MHz | 1605 MHz |
| Boost Clock | 2535 MHz | 1770 MHz |
| Shading Units | 4352 | 2560 |
| Texture Mapping Units (TMUs) | 136 | 160 |
| Render Output Units (ROPs) | 48 | 64 |
| Compute Units (Pipelines) | 34 | 40 |
| Tensor Cores | 136 | 320 |
| Ray-tracing Cores | 34 | 40 |
| L1 Cache | 128KB per cluster | 64KB per cluster |
| L2 Cache | 32MB shared | 4MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 122 GPixel/s | 113 GPixel/s |
| Texture Fill Rate | 345 GTexel/s | 283 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | PCIe 3.0 x16 |
| TGP | 165 W | 215 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 12 nm |
| Die Size | 188 mm² | 545 mm² |
| Transistor Count | 22 billion | 13 billion |
| Transistor Density | 117.02 MTr/mm² | 23.85 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 16 GB | 8 GB |
| Memory Clock | 2250 MHz | 1750 MHz |
| Effective Memory Speed | 18000 Mbps | 14000 Mbps |
| Bus | 128-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 | 7.5 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 2 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 12