Nvidia GeForce RTX 3070 Laptop vs Nvidia GeForce RTX 3070 Ti Laptop
40
out 100
VS
42
out 100
Compared 2 processors: Nvidia GeForce RTX 3070 Laptop, vs Nvidia GeForce RTX 3070 Ti Laptop. Below are specs, tests, pros and cons for each device
Review
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
Tests & specs
Specs & test comparisonGames
| Game title | 1080p (High) 1080p (Ultra) 1440p (Ultra) 4K (Ultra) | |
 Forza Horizon 5 | 123 79 68 45 | 134 82 72 52 |
 The Witcher 3 | 141 112 83 46 | 151 120 88 47 |
 Counter-Strike 2 | 201 153 112 54 | 219 165 120 64 |
 Far Cry 6 | 106 92 76 39 | 114 103 83 44 |
 Hogwarts Legacy | 76 63 46 25 | 82 71 50 27 |
 COD Modern Warfare 3 | 96 86 60 40 | 103 97 68 42 |
 Ghost of Tsushima | 71 59 44 25 | 77 64 48 25 |
 Cyberpunk 2077 | 84 72 45 22 | 92 82 47 24 |
 Shadow of the Tomb Raider | 125 115 83 45 | 140 126 93 49 |
| 1080p High | 114 | 124 |
| 1080p Ultra | 92 | 101 |
| 1440p Ultra | 69 | 74 |
| 4K Ultra | 38 | 42 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 10479 | 11342 |
| Solar Bay | 45677 | 49735 |
| Port Royal | 6250 | 6849 |
| Fire Strike | 26767 | 28618 |
| Night Raid | 83274 | 95219 |
| Background Blur | 170.3 frames/s | 173.8 frames/s |
| Face Detection | 113.6 frames/s | 96.9 frames/s |
| Horizon Detection | 5.59 Gpix/sec | 5.69 Gpix/sec |
| Edge Detection | 7.94 Gpix/sec | 7.75 Gpix/sec |
| Gaussian Blur | 6.19 Gpix/sec | 6.27 Gpix/sec |
| Feature Matching | 1.16 Gpix/sec | 1.14 Gpix/sec |
| Stereo Matching | 467 Gpix/sec | 480.4 Gpix/sec |
| Particle Physics | 15131.3 fps | 14706.2 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 644 | 778 |
| DirectX 11 | 138 fps | 154 fps |
| DirectX 12 | 64 fps | 74 fps |
| GPU Compute | 6902 Ops/s | 7564 Ops/s |
| Aztec Ruins (Normal) | 644.4 fps | 730.7 fps |
| Car Chase | 565.3 fps | 624.6 fps |
| Manhattan 3.1.1 (1440p) | 483.8 fps | 540.8 fps |
| T-Rex | 2380.5 fps | 2606.1 fps |
| ALU 2 | 3169.7 fps | 3639.9 fps |
| Driver Overhead 2 | 246.7 fps | 256.5 fps |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
| Tessellation | 3511.5 | 3852.5 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Announced | January, 12, 2021 | n/a |
| Form Factor | Laptop use | Laptop use |
| Use case | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ampere | Ampere |
| Codename | GA104 (GN20-E5) | GA104 (GN20-E6) |
GPU
| GPU Frequency | 780-1215 MHz | 510-1035 MHz |
| Boost GPU Frequency | 1290-1620 MHz | 1035-1485 MHz |
| Shader Units | 5120 | 5632 |
| TMUs | 160 | 176 |
| ROPs | 80 | 80 |
| Execution Units | 40 | 44 |
| Ray Tracing Cores | 40 | 44 |
| Tensor Cores | 160 | 176 |
| L1 cache | 128 KB/core | 128 KB/core |
| L2 cache | 4000 KB/core | 4000 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 103-130 Gpix/sec | 83-119 Gpix/sec |
| Texture Fill Rate | 206-259 GTex/s | 182-261 GTex/s |
| FLOPS | 13.2-16.6 TFLOPS | 11.7-16.7 TFLOPS |
Process
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 80-150 W | 80-150 W |
| Process | Samsung | Samsung |
| Process tech. | 8 nm | 8 nm |
| Transistor Size | 392 mm² | 392 mm² |
| Transistor count | 17.4 billion | 17.4 billion |
| Transistor density | 44.39 MTr/mm² | 44.39 MTr/mm² |
Memory
| Interface | GDDR6 | GDDR6 |
| Memory Frequency | 1500-1750 MHz | 1750 MHz |
| Bus | 256 bit | 256 bit |
| ECC support | No | No |
| Effective Memory Speed | 12000-14000 MB/s | 14000 MB/s |
| Memory Size | 8 GB | 8 GB |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.2 | 1.2 |
| OpenGL | 4.6 | 4.6 |
| CUDA | 8.6 | 8.6 |
| DisplayPort | 1.4a | 1.4a |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 2 | DLSS 2 |
Results
No clear favorite identified yet; updates may follow as new data arrives.
Survey
Total Votes: 0
