GeForce RTX 3060 vs RTX 2070
VS
Nvidia GeForce RTX 3060
GA106
Nvidia GeForce RTX 2070
TU106
We compared two discrete desktop gaming GPUs: the GeForce RTX 3060 12 GB with 28 pipelines and 3584 shaders against the 2 years and 3 months older RTX RTX 2070 8 GB that utilizes 36 pipelines and 2304 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 3060
- 69% higher maximum theoretical performance (12.7 vs 7.5 TFLOPS)
- Manufactured using a more efficient 8 nm process technology
- Includes 4 GB more video memory
- Has 56% more shading units (3584 vs 2304)
Reasons to consider the GeForce RTX 2070
- Features 176 more tensor cores for effective ML and AI workloads
- Has 24% higher memory bandwidth: 448 vs 360 GB/s
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 112 68 60 39 |
109 70 56 40 |
| The Witcher 3 | 122 100 74 39 |
124 100 73 38 |
| Counter-Strike 2 | 181 137 99 48 |
181 132 96 48 |
| Far Cry 6 | 95 85 67 37 |
92 83 64 34 |
| Hogwarts Legacy | 65 57 40 18 |
65 56 41 19 |
| CoD: Modern Warfare III | 80 74 53 31 |
79 74 50 34 |
| Ghost of Tsushima | 62 50 37 20 |
64 50 36 20 |
| Cyberpunk 2077 | 68 64 38 16 |
67 63 35 15 |
| Shadow of the Tomb Raider | 109 98 70 36 |
106 98 68 36 |
| 1080p High | 99 | 99 |
| 1080p Ultra | 81 | 81 |
| 1440p Ultra | 60 | 58 |
| 4K Ultra | 32 | 32 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 8754 | 9074 |
| Solar Bay | 41158 | 39675 |
| Port Royal | 5145 | 5194 |
| Fire Strike | 22304 | 23208 |
| Wild Life Extreme | 17728 | 18257 |
| Night Raid | 97159 | 92357 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 149.6 img/sec | 200 img/sec |
| Face Detection | 91 img/sec | 106.8 img/sec |
| Horizon Detection | 4.07 Gpixels/sec | 3.73 Gpixels/sec |
| Edge Detection | 5.58 Gpixels/sec | 4.57 Gpixels/sec |
| Gaussian Blur | 3.92 Gpixels/sec | 4.84 Gpixels/sec |
| Feature Matching | 1.01 Gpixels/sec | 1.07 Gpixels/sec |
| Stereo Matching | 372.9 Gpixels/sec | 452 Gpixels/sec |
| Particle Physics | 12226.3 FPS | 11141.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 965 | 816 |
| DirectX 11 | 127 FPS | 130 FPS |
| DirectX 12 | 68 FPS | 61 FPS |
| GPU Compute | 8231 Ops/s | 6376 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 3060
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-07 (tach) | Cinebench 2024 | 7952 |
GeForce RTX 2070
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) | 6645 | 5244 |
| Image Segmentation (HP) | 15338 | 9644 |
| Image Super Resolution (Q) | 14283 | 13716 |
| Face Detection (HP) | 28862 | 21326 |
| Pose Estimation (Q) | 61313 | 57284 |
| Text Classification (SP) | 2463 | 1857 |
| Machine Translation (HP) | 3793 | 2542 |
| Object Detection (SP) | 7712 | 6466 |
| Depth Estimation (Q) | 25461 | 22978 |
| Style Transfer (SP) | 123233 | 111896 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 3060 and RTX 2070General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 12, 2021 | October 17, 2018 |
| Launch price (MSRP) | $329 | $599 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ampere | Turing |
| GPU Codename | GA106 | TU106 |
| Rival Equivalent | - Radeon RX 6700 XT | - Radeon RX 5700 XT |
| Successor | - GeForce RTX 5060 | - GeForce RTX 5070 |
| Recommended CPU | - Intel Core i5 12600K or above | - Intel Core i7 9700K or above |
Desktop GPU rating (57th and 63rd place)
Graphics Processing Unit
| Base Clock | 1320 MHz | 1410 MHz |
| Boost Clock | 1777 MHz | 1620 MHz |
| Shading Units | 3584 | 2304 |
| Texture Mapping Units (TMUs) | 112 | 144 |
| Render Output Units (ROPs) | 48 | 64 |
| Compute Units (Pipelines) | 28 | 36 |
| Tensor Cores | 112 | 288 |
| Ray-tracing Cores | 28 | 36 |
| L1 Cache | 128KB per cluster | 64KB per cluster |
| L2 Cache | 3MB shared | 4MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 85 GPixel/s | 104 GPixel/s |
| Texture Fill Rate | 199 GTexel/s | 233 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| TGP | 170 W | 175 W |
| Manufacturing | Samsung | TSMC |
| Fabrication Process | 8 nm | 12 nm |
| Die Size | 276 mm² | 445 mm² |
| Transistor Count | 12 billion | 10 billion |
| Transistor Density | 43.48 MTr/mm² | 22.47 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 12 GB | 8 GB |
| Memory Clock | 1875 MHz | 1750 MHz |
| Effective Memory Speed | 15000 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 | 8.6 | 7.5 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 2 | DLSS 2 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 110