GeForce RTX 4070 Laptop vs 3080 Ti Laptop
VS
Nvidia GeForce RTX 4070 Laptop
AD106 (GN21-X6)
Nvidia GeForce RTX 3080 Ti Laptop
GA103 (GN20-E8)
We compared two discrete laptop gaming GPUs: the GeForce RTX 4070 Mobile 8 GB with 36 pipelines and 4608 shaders against the 1 year and 2 months older RTX 3080 Ti Mobile 16 GB that utilizes 58 pipelines and 7424 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
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 3080 Ti Laptop
- 18% higher maximum theoretical performance (23.6 vs 20 TFLOPS)
- Includes 8 GB more video memory
- Has 2x higher memory bandwidth: 512 vs 256 GB/s
- Features 88 more tensor cores for effective ML and AI workloads
- Has 61% more shading units (7424 vs 4608)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 139 89 77 56 |
143 91 81 57 |
| The Witcher 3 | 164 129 95 53 |
164 136 98 55 |
| Counter-Strike 2 | 236 183 130 71 |
238 181 129 72 |
| Far Cry 6 | 121 109 87 51 |
123 111 88 51 |
| Hogwarts Legacy | 91 77 60 28 |
95 75 57 30 |
| CoD: Modern Warfare III | 111 105 77 51 |
116 106 78 49 |
| Ghost of Tsushima | 85 69 53 29 |
87 70 56 29 |
| Cyberpunk 2077 | 99 84 53 25 |
99 90 57 27 |
| Shadow of the Tomb Raider | 147 137 100 53 |
150 138 103 57 |
| 1080p High | 133 | 135 |
| 1080p Ultra | 109 | 111 |
| 1440p Ultra | 81 | 83 |
| 4K Ultra | 46 | 47 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 12514 | 12862 |
| Solar Bay | 54815 | 56131 |
| Port Royal | 7416 | 8091 |
| Fire Strike | 30057 | 30852 |
| Wild Life Extreme | 23262 | 26346 |
| Night Raid | 113672 | 98742 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 158.5 img/sec | 200.9 img/sec |
| Face Detection | 116.5 img/sec | 131.2 img/sec |
| Horizon Detection | 4.35 Gpixels/sec | 6.49 Gpixels/sec |
| Edge Detection | 5.67 Gpixels/sec | 8.9 Gpixels/sec |
| Gaussian Blur | 6.44 Gpixels/sec | 6.34 Gpixels/sec |
| Feature Matching | 1.36 Gpixels/sec | 1.2 Gpixels/sec |
| Stereo Matching | 528.5 Gpixels/sec | 571 Gpixels/sec |
| Particle Physics | 16372.3 FPS | 17240.3 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 766 | 813 |
| DirectX 11 | 177 FPS | 160 FPS |
| DirectX 12 | 85 FPS | 86 FPS |
| GPU Compute | 8365 Ops/s | 8216 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 4070 Laptop
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-06-05 (Wahid) | GeekBench | 122515 |
| 📘 2026-06-05 (Wahid) | GeekBench | 35869 |
GeForce RTX 3080 Ti Laptop
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) | 8642 | 6797 |
| Image Segmentation (HP) | 20635 | 20808 |
| Image Super Resolution (Q) | 26378 | 15194 |
| Face Detection (HP) | 39776 | 37084 |
| Pose Estimation (Q) | 105983 | 82268 |
| Text Classification (SP) | 2995 | 2863 |
| Machine Translation (HP) | 4507 | 4135 |
| Object Detection (SP) | 10198 | 8559 |
| Depth Estimation (Q) | 41078 | 28330 |
| Style Transfer (SP) | 190315 | 184129 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 4070 Laptop and 3080 Ti LaptopGeneral
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | February 22, 2023 | January 1, 2022 |
| Case | Laptop | Laptop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ada Lovelace | Ampere |
| GPU Codename | AD106 (GN21-X6) | GA103 (GN20-E8) |
| Successor | - GeForce RTX 5070 Laptop | - GeForce RTX 5090 Laptop |
| Recommended CPU | - Intel Core Ultra 7 155H or above | - Intel Core i9 12900H or above |
Laptop GPU ranking (22nd and 25th place)
Graphics Processing Unit
| Base Clock | 735-2070 MHz (configurable) | 585-1230 MHz (configurable) |
| Boost Clock | 1230-2175 MHz (configurable) | 1125-1590 MHz (configurable) |
| Shading Units | 4608 | 7424 |
| Texture Mapping Units (TMUs) | 144 | 232 |
| Render Output Units (ROPs) | 48 | 96 |
| Compute Units (Pipelines) | 36 | 58 |
| Tensor Cores | 144 | 232 |
| Ray-tracing Cores | 36 | 58 |
| 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 | 108-153 GPixel/s |
| Texture Fill Rate | 177-313 GTexel/s | 261-369 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 35-140 W (configurable) | 80-175 W (configurable) |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 5 nm | 8 nm |
| Die Size | 186 mm² | 496 mm² |
| Transistor Count | 22.9 billion | 22 billion |
| Transistor Density | 123.12 MTr/mm² | 44.35 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 8 GB | 16 GB |
| Memory Clock | 2000 MHz | 2000 MHz |
| Effective Memory Speed | 16000 Mbps | 16000 Mbps |
| Bus | 128-bit | 256-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.2 |
| 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: 148