GeForce RTX 4070 vs RTX 4060
VS
Nvidia GeForce RTX 4070
AD104
Nvidia GeForce RTX 4060
AD107
We compared two discrete desktop gaming GPUs: the GeForce RTX 4070 12 GB with 46 pipelines and 5888 shaders against the RTX RTX 4060 8 GB that utilizes 24 pipelines and 3072 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 69%) in 3DMark Steel Nomad Lite
- 93% higher maximum theoretical performance (29.1 vs 15.1 TFLOPS)
- Shows 54% higher average frame rate in modern games at QHD resolution – 106 vs 69 FPS
- Includes 4 GB more video memory
- Features 88 more tensor cores for effective ML and AI workloads
- Has 85% higher memory bandwidth: 504 vs 272 GB/s
- Achieves 57% more points in the GeekBench 6 Compute test (167K vs 106K)
- Has 92% more shading units (5888 vs 3072)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 172 115 102 79 |
128 78 66 47 |
| The Witcher 3 | 194 159 114 61 |
143 117 82 44 |
| Counter-Strike 2 | 272 205 149 81 |
208 157 111 58 |
| Far Cry 6 | 149 133 115 68 |
105 98 76 45 |
| Hogwarts Legacy | 117 97 77 39 |
78 65 47 26 |
| CoD: Modern Warfare III | 149 145 107 69 |
98 90 64 43 |
| Ghost of Tsushima | 106 88 72 43 |
73 61 45 27 |
| Cyberpunk 2077 | 129 119 75 37 |
82 75 43 22 |
| Shadow of the Tomb Raider | 211 190 145 80 |
128 119 85 46 |
| 1080p High | 167 | 116 |
| 1080p Ultra | 139 | 96 |
| 1440p Ultra | 106 | 69 |
| 4K Ultra | 62 | 40 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 17799 | 10615 |
| Solar Bay | 82861 | 49340 |
| Port Royal | 11156 | 6054 |
| Fire Strike | 44067 | 28540 |
| Wild Life Extreme | 35472 | 20610 |
| Night Raid | 153385 | 121368 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 233 img/sec | 186.9 img/sec |
| Face Detection | 141.7 img/sec | 112.7 img/sec |
| Horizon Detection | 6.62 Gpixels/sec | 3.92 Gpixels/sec |
| Edge Detection | 9.19 Gpixels/sec | 5.16 Gpixels/sec |
| Gaussian Blur | 9.2 Gpixels/sec | 4.94 Gpixels/sec |
| Feature Matching | 1.78 Gpixels/sec | 1.34 Gpixels/sec |
| Stereo Matching | 845.4 Gpixels/sec | 446.2 Gpixels/sec |
| Particle Physics | 25043.9 FPS | 14935.1 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1165 | 1036 |
| DirectX 11 | 243 FPS | 174 FPS |
| DirectX 12 | 103 FPS | 76 FPS |
| GPU Compute | 14561 Ops/s | 9150 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 4070
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-14 (kashitsu) | Cinebench 2024 | 18051 |
GeForce RTX 4060
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-03-21 (John Fernand) | Geekbench 6 OpenCL | 105636 |
| 📘 2026-03-21 (John Fernand) | Cinebench 2024 | 10606 |
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 | 7696 |
| Image Segmentation (HP) | 26153 | 13706 |
| Image Super Resolution (Q) | 32054 | 23289 |
| Face Detection (HP) | 51337 | 31126 |
| Pose Estimation (Q) | 124617 | 78361 |
| Text Classification (SP) | 3703 | 3315 |
| Machine Translation (HP) | 5484 | 3491 |
| Object Detection (SP) | 13134 | 9386 |
| Depth Estimation (Q) | 50548 | 36778 |
| Style Transfer (SP) | 263477 | 148120 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 4070 and RTX 4060General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | April 13, 2023 | May 18, 2023 |
| Launch price (MSRP) | $599 | $299 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | Ada Lovelace | Ada Lovelace |
| GPU Codename | AD104 | AD107 |
| Rival Equivalent | - Radeon RX 7900 XT | - Radeon RX 7700 XT |
| Successor | - GeForce RTX 5070 | - GeForce RTX 5060 |
| Recommended CPU | - Intel Core i7 14700K or above | - Intel Core i5 14600K or above |
Desktop GPU rating (30th and 54th place)
Graphics Processing Unit
| Base Clock | 1920 MHz | 1830 MHz |
| Boost Clock | 2475 MHz | 2460 MHz |
| Shading Units | 5888 | 3072 |
| Texture Mapping Units (TMUs) | 184 | 96 |
| Render Output Units (ROPs) | 64 | 48 |
| Compute Units (Pipelines) | 46 | 24 |
| Tensor Cores | 184 | 96 |
| Ray-tracing Cores | 46 | 24 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 36MB shared | 24MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 158 GPixel/s | 118 GPixel/s |
| Texture Fill Rate | 455 GTexel/s | 236 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x8 |
| TGP | 200 W | 115 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 5 nm |
| Die Size | 294 mm² | 159 mm² |
| Transistor Count | 35 billion | 18 billion |
| Transistor Density | 119.05 MTr/mm² | 113.21 MTr/mm² |
Memory
| Memory Type | GDDR6X | GDDR6 |
| Memory Size | 12 GB | 8 GB |
| Memory Clock | 1313 MHz | - |
| Effective Memory Speed | 21000 Mbps | - |
| Bus | 192-bit | 128-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: 136