GeForce RTX 4070 Laptop vs RTX 3070
VS
Nvidia GeForce RTX 4070 Laptop
AD106 (GN21-X6)
Nvidia GeForce RTX 3070
GA104
We performed a head-to-head comparison of the GeForce RTX 4070 Mobile with 36 pipelines and 4608 shaders against the 2 years and 4 months older RTX RTX 3070 that utilizes 46 pipelines and 5888 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Some GPUs come in different configurations. For greater precision, pick a specific config below
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
The "Energy Efficiency" metric has less impact on the NanoReview Score for desktop GPU.
Key differences
Reasons to consider the GeForce RTX 4070 Laptop
- Manufactured using a more efficient 5 nm process technology
- Supports Nvidia DLSS 3 technology
Reasons to consider the GeForce RTX 3070
- Shows 9% higher average frame rate in modern games at QHD resolution – 88 vs 81 FPS
- Has 75% higher memory bandwidth: 448 vs 256 GB/s
- Has 28% more shading units (5888 vs 4608)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 139 89 77 56 |
147 99 86 61 |
| The Witcher 3 | 164 129 95 53 |
168 143 100 54 |
| Counter-Strike 2 | 236 183 130 71 |
244 194 137 77 |
| Far Cry 6 | 121 109 87 51 |
132 121 96 54 |
| Hogwarts Legacy | 91 77 60 28 |
97 80 62 35 |
| CoD: Modern Warfare III | 111 105 77 51 |
121 113 85 52 |
| Ghost of Tsushima | 85 69 53 29 |
89 74 56 31 |
| Cyberpunk 2077 | 99 84 53 25 |
106 94 59 28 |
| Shadow of the Tomb Raider | 147 137 100 53 |
165 153 113 60 |
| 1080p High | 133 | 141 |
| 1080p Ultra | 109 | 119 |
| 1440p Ultra | 81 | 88 |
| 4K Ultra | 46 | 50 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 12514 | 13644 |
| Solar Bay | 54815 | 64452 |
| Port Royal | 7416 | 8312 |
| Fire Strike | 30057 | 34056 |
| Wild Life Extreme | 23262 | 28488 |
| Night Raid | 113672 | 122159 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 158.5 img/sec | 161.6 img/sec |
| Face Detection | 116.5 img/sec | 117.2 img/sec |
| Horizon Detection | 4.35 Gpixels/sec | 5.89 Gpixels/sec |
| Edge Detection | 5.67 Gpixels/sec | 8.05 Gpixels/sec |
| Gaussian Blur | 6.44 Gpixels/sec | 6.65 Gpixels/sec |
| Feature Matching | 1.36 Gpixels/sec | 1.25 Gpixels/sec |
| Stereo Matching | 528.5 Gpixels/sec | 550.6 Gpixels/sec |
| Particle Physics | 16372.3 FPS | 17613.1 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 766 | 1005 |
| DirectX 11 | 177 FPS | 183 FPS |
| DirectX 12 | 85 FPS | 84 FPS |
| GPU Compute | 8365 Ops/s | 11007 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 4070 Laptop
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-06-05 (Wahid) | Geekbench 6 OpenCL | 122515 |
| 📘 2026-06-05 (Wahid) | Geekbench 6 OpenCL | 35869 |
GeForce RTX 3070
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-11-15 (mit) | Cinebench 2024 | 9652 |
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) | 8642 | 7624 |
| Image Segmentation (HP) | 20635 | 23420 |
| Image Super Resolution (Q) | 26378 | 17898 |
| Face Detection (HP) | 39776 | 40535 |
| Pose Estimation (Q) | 105983 | 83624 |
| Text Classification (SP) | 2995 | 2724 |
| Machine Translation (HP) | 4507 | 4481 |
| Object Detection (SP) | 10198 | 10304 |
| Depth Estimation (Q) | 41078 | 30418 |
| Style Transfer (SP) | 190315 | 180089 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 4070 Laptop and RTX 3070General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | February 22, 2023 | October 22, 2020 |
| Launch price (MSRP) | - | $499 |
| Case | Laptop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | Ada Lovelace | Ampere |
| GPU Codename | AD106 (GN21-X6) | GA104 |
| Rival Equivalent | - | - Radeon RX 7800 XT |
| Successor | - GeForce RTX 5070 Laptop | - GeForce RTX 5070 |
| Recommended CPU | - Intel Core Ultra 7 155H or above | - Intel Core i7 12700K or above |
Laptop GPU ranking (#23rd place)
Desktop GPU rating (#44th place)
Graphics Processing Unit
| Base Clock | 735-2070 MHz (configurable) | 1500 MHz |
| Boost Clock | 1230-2175 MHz (configurable) | 1725 MHz |
| Shading Units | 4608 | 5888 |
| Texture Mapping Units (TMUs) | 144 | 184 |
| Render Output Units (ROPs) | 48 | 96 |
| Compute Units (Pipelines) | 36 | 46 |
| Tensor Cores | 144 | 184 |
| Ray-tracing Cores | 36 | 46 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 32MB shared | 4MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 59-104 GPixel/s | 166 GPixel/s |
| Texture Fill Rate | 177-313 GTexel/s | 317 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 35-140 W (configurable) | 220 W |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 5 nm | 8 nm |
| Die Size | 186 mm² | 392 mm² |
| Transistor Count | 22.9 billion | 17 billion |
| Transistor Density | 123.12 MTr/mm² | 43.37 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 8 GB | 8 GB |
| Memory Clock | 2000 MHz | 1750 MHz |
| Effective Memory Speed | 16000 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 | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 2 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 64