[ GEFORCE ]
Graphics Cards
GeForce GTX 1070 Ti
Overall Score
23/100
Key Technical Specifications
Graphics (GPU)
Pascal
[ EXPERT VERDICT · SUMMARY ]
GeForce GTX 1070 Ti is an engineering-tested graphics cards achieving an overall rating of 23/100. It is positioned for balanced everyday compute and power efficiency.
Benchmark Performance Scores
Normalized 0–100 Scale
Efficiency
Rating: Poor
20/100
Gaming
Rating: Poor
22/100
Detailed Technical Specifications
3D Mark
| Specification | Value |
|---|---|
| Fire Strike | 20113 |
| Night Raid | 78888 |
| Port Royal | 1554 |
| Solar Bay | 18306 |
| Time Spy | 6842 |
| Wild Life Extreme | 13255 |
API
| Specification | Value |
|---|---|
| CUDA | 6.1 |
| DLSS | No |
| DirectX | 12 |
| DisplayPort | 1.4a |
| OpenCL | 3.0 |
| OpenGL | 4.6 |
| Ray Tracing | No |
| Vulkan | 1.3 |
Games
| Specification | Value |
|---|---|
| 1080p High | 80 |
| 1080p Ultra | 63 |
| 1440p Ultra | 45 |
| 4K Ultra | 23 |
| CoD: Modern Warfare III | 63523723 |
| Counter-Strike 2 | 1491047837 |
| Cyberpunk 2077 | 51482612 |
| Far Cry 6 | 78705225 |
| Forza Horizon 5 | 97564529 |
| Ghost of Tsushima | 49372613 |
| Hogwarts Legacy | 54423116 |
| Margin of Error | Low |
| Shadow of the Tomb Raider | 87775328 |
| The Witcher 3 | 95775327 |
GeekBench 6 ML
| Specification | Value |
|---|---|
| Backend | DirectML |
| Depth Estimation (Q) | 14316 |
| Face Detection (HP) | 9306 |
| Framework | ONNX |
| Image Classification (SP) | 3473 |
| Image Segmentation (HP) | 5149 |
| Image Super Resolution (Q) | 9722 |
| Machine Translation (HP) | 2424 |
| Object Detection (SP) | 4566 |
| Pose Estimation (Q) | 34870 |
| Style Transfer (SP) | 88984 |
| Text Classification (SP) | 2139 |
GeekBench 6 OpenCL
| Specification | Value |
|---|---|
| API | OpenCL |
| Background Blur | 149.2 img/sec |
| Edge Detection | 3.57 Gpixels/sec |
| Face Detection | 67.6 img/sec |
| Feature Matching | 0.27 Gpixels/sec |
| Gaussian Blur | 4.32 Gpixels/sec |
| Horizon Detection | 2.36 Gpixels/sec |
| Particle Physics | 6584.9 FPS |
| Stereo Matching | 209.6 Gpixels/sec |
General
| Specification | Value |
|---|---|
| AMD Equivalent | -Radeon RX 5600 XT |
| Architecture | Pascal |
| Build | Discrete |
| Case | Desktop |
| GPU Codename | GP104 |
| Purpose | Gaming |
| Recommended CPU | -Intel Core i7 7700Kor above |
| Released | November 2, 2017 |
| Segment | Mid-range |
| Vendor | Nvidia |
Graphics Processing Unit
| Specification | Value |
|---|---|
| Base Clock | 1607 MHz |
| Boost Clock | 1683 MHz |
| Compute Units (Pipelines) | 19 |
| Instructions Per Cycle | 2 IPC |
| L1 Cache | 48KB per cluster |
| L2 Cache | 2MB shared |
| Ray-tracing Cores | No |
| Render Output Units (ROPs) | 64 |
| Shading Units | 2432 |
| Tensor Cores | No |
| Texture Mapping Units (TMUs) | 152 |
Memory
| Specification | Value |
|---|---|
| Bus | 256-bit |
| ECC | No |
| Effective Memory Speed | 8000 Mbps |
| Memory Clock | 2002 MHz |
| Memory Size | 8 GB |
| Memory Type | GDDR5 |
Passmark Graphics
| Specification | Value |
|---|---|
| DirectX 11 | 106 FPS |
| DirectX 12 | 52 FPS |
| G2D Mark | 876 |
| GPU Compute | 7166 Ops/s |
Physical
| Specification | Value |
|---|---|
| Die Size | 314 mm² |
| Fabrication Process | 16 nm |
| Interface | PCIe 3.0 x16 |
| Manufacturing | TSMC |
| TGP | 180 W |
| Transistor Count | 7 billion |
| Transistor Density | 22.29 MTr/mm² |
Raw Performance
| Specification | Value |
|---|---|
| Pixel Fill Rate | 108 GPixel/s |
| Texture Fill Rate | 256 GTexel/s |
Strengths & Limitations
Key Advantages
- Comprehensive positive benchmark metrics recorded.
Key Considerations
- No major hardware limitations flagged during benchmark run.
Direct Competitors & Alternatives
NVIDIA
Nvidia RTX Pro 6000 Blackwell
98/100
Compare →
GEFORCE
GeForce RTX 5090
96/100
Compare →
GEFORCE
GeForce RTX 4090
89/100
Compare →
AMD
AMD Radeon RX 7900 XTX
85/100
Compare →
Methodology, Provenance & Verification
Score version 2026.1 · Data verified 2026-08-26 · Source: official manufacturer datasheets and standardized reproducible benchmark suites (Geekbench 6, Cinebench R24, 3DMark).