GeForce RTX 3060 vs GTX 1070
VS
Nvidia GeForce RTX 3060
GA106
Nvidia GeForce GTX 1070
GP104
We compared two discrete desktop gaming GPUs: the GeForce RTX 3060 12 GB with 28 pipelines and 3584 shaders against the 5 years and 1 month older GTX 1070 8 GB that utilizes 15 pipelines and 1920 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
- Performs significantly better (up to 54%) in 3DMark Steel Nomad Lite
- 2x higher maximum theoretical performance (12.7 vs 6.5 TFLOPS)
- Manufactured using a more efficient 8 nm process technology
- Shows 50% higher average frame rate in modern games at QHD resolution – 60 vs 40 FPS
- Ray-tracing support with 28 dedicated RT cores
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 112 68 60 39 |
88 50 41 25 |
| The Witcher 3 | 122 100 74 39 |
83 68 47 25 |
| Counter-Strike 2 | 181 137 99 48 |
135 95 68 32 |
| Far Cry 6 | 95 85 67 37 |
73 64 47 24 |
| Hogwarts Legacy | 65 57 40 18 |
45 38 29 13 |
| CoD: Modern Warfare III | 80 74 53 31 |
54 49 33 22 |
| Ghost of Tsushima | 62 50 37 20 |
43 31 24 13 |
| Cyberpunk 2077 | 68 64 38 16 |
45 44 24 10 |
| Shadow of the Tomb Raider | 109 98 70 36 |
79 73 48 25 |
| 1080p High | 99 | 72 |
| 1080p Ultra | 81 | 57 |
| 1440p Ultra | 60 | 40 |
| 4K Ultra | 32 | 21 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 8754 | 6091 |
| Solar Bay | 41158 | 16030 |
| Port Royal | 5145 | 1283 |
| Fire Strike | 22304 | 18705 |
| Wild Life Extreme | 17728 | 12186 |
| Night Raid | 97159 | 72459 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 149.6 img/sec | 142.3 img/sec |
| Face Detection | 91 img/sec | 65.1 img/sec |
| Horizon Detection | 4.07 Gpixels/sec | 2.2 Gpixels/sec |
| Edge Detection | 5.58 Gpixels/sec | 3.23 Gpixels/sec |
| Gaussian Blur | 3.92 Gpixels/sec | 3.74 Gpixels/sec |
| Feature Matching | 1.01 Gpixels/sec | 0.3 Gpixels/sec |
| Stereo Matching | 372.9 Gpixels/sec | 195.6 Gpixels/sec |
| Particle Physics | 12226.3 FPS | 5161.6 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 965 | 848 |
| DirectX 11 | 127 FPS | 99 FPS |
| DirectX 12 | 68 FPS | 49 FPS |
| GPU Compute | 8231 Ops/s | 6123 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 3060
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-07 (tach) | Cinebench 2024 | 7952 |
GeForce GTX 1070
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-08-09 (yourtrain) | Geekbench 6 OpenCL | 53862 |
| 📘 2026-08-09 (yourtrain) | Cinebench 2024 | 3551 |
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 | 2295 |
| Image Segmentation (HP) | 15338 | 4955 |
| Image Super Resolution (Q) | 14283 | 10587 |
| Face Detection (HP) | 28862 | 8747 |
| Pose Estimation (Q) | 61313 | 51263 |
| Text Classification (SP) | 2463 | 1461 |
| Machine Translation (HP) | 3793 | 2342 |
| Object Detection (SP) | 7712 | 2960 |
| Depth Estimation (Q) | 25461 | 15275 |
| Style Transfer (SP) | 123233 | 104907 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 3060 and GTX 1070General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 12, 2021 | January 10, 2016 |
| Launch price (MSRP) | $329 | $379 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ampere | Pascal |
| GPU Codename | GA106 | GP104 |
| Rival Equivalent | - Radeon RX 6700 XT | - Radeon RX 5600 XT |
| Successor | - GeForce RTX 5060 | - GeForce RTX 5070 |
| Recommended CPU | - Intel Core i5 12600K or above | - Intel Core i7 7700K or above |
Desktop GPU rating (58th and 76th place)
Graphics Processing Unit
| Base Clock | 1320 MHz | 1506 MHz |
| Boost Clock | 1777 MHz | 1683 MHz |
| Shading Units | 3584 | 1920 |
| Texture Mapping Units (TMUs) | 112 | 120 |
| Render Output Units (ROPs) | 48 | 64 |
| Compute Units (Pipelines) | 28 | 15 |
| Tensor Cores | 112 | No |
| Ray-tracing Cores | 28 | No |
| L1 Cache | 128KB per cluster | 48KB per cluster |
| L2 Cache | 3MB shared | 2MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 85 GPixel/s | 108 GPixel/s |
| Texture Fill Rate | 199 GTexel/s | 202 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| TGP | 170 W | 150 W |
| Manufacturing | Samsung | TSMC |
| Fabrication Process | 8 nm | 16 nm |
| Die Size | 276 mm² | 314 mm² |
| Transistor Count | 12 billion | 7 billion |
| Transistor Density | 43.48 MTr/mm² | 22.29 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR5 |
| Memory Size | 12 GB | 8 GB |
| Memory Clock | 1875 MHz | 2002 MHz |
| Effective Memory Speed | 15000 Mbps | 8000 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 | 6.1 |
| Ray Tracing | Yes | No |
| DLSS | DLSS 2 | No |
| DisplayPort | 1.4a | 1.4a |
Further details
Notes on GTX 1070:
- There's a version with GDDR5X memory.
Cast your vote
Total votes: 71