GeForce GTX 1660 SUPER vs GTX 1070
VS
Nvidia GeForce GTX 1070
GP104
We compared two discrete desktop gaming GPUs: the GeForce GTX 1660 SUPER 6 GB with 22 pipelines and 1408 shaders against the 3 years and 11 months older GTX 1070 8 GB that utilizes 15 pipelines and 1920 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 GTX 1660 SUPER
- Manufactured using a more efficient 12 nm process technology
- Has 31% higher memory bandwidth: 336 vs 256.3 GB/s
- Achieves 26% more points in the GeekBench 6 Compute test (67K vs 53K)
Reasons to consider the GeForce GTX 1070
- 30% higher maximum theoretical performance (6.5 vs 5 TFLOPS)
- Includes 2 GB more video memory
- Has 36% more shading units (1920 vs 1408)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 86 51 43 25 |
88 50 41 25 |
| The Witcher 3 | 83 65 47 26 |
83 68 47 25 |
| Counter-Strike 2 | 133 93 68 29 |
135 95 68 32 |
| Far Cry 6 | 70 62 46 24 |
73 64 47 24 |
| Hogwarts Legacy | 46 36 26 13 |
45 38 29 13 |
| CoD: Modern Warfare III | 55 44 31 19 |
54 49 33 22 |
| Ghost of Tsushima | 41 34 26 12 |
43 31 24 13 |
| Cyberpunk 2077 | 44 40 22 11 |
45 44 24 10 |
| Shadow of the Tomb Raider | 77 71 47 23 |
79 73 48 25 |
| 1080p High | 71 | 72 |
| 1080p Ultra | 55 | 57 |
| 1440p Ultra | 40 | 40 |
| 4K Ultra | 20 | 21 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 6042 | 6091 |
| Solar Bay | 19265 | 16030 |
| Port Royal | 1547 | 1283 |
| Fire Strike | 16189 | 18705 |
| Wild Life Extreme | 12334 | 12186 |
| Night Raid | 74735 | 72459 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 122.5 img/sec | 142.3 img/sec |
| Face Detection | 68.6 img/sec | 65.1 img/sec |
| Horizon Detection | 2.56 Gpixels/sec | 2.2 Gpixels/sec |
| Edge Detection | 3.33 Gpixels/sec | 3.23 Gpixels/sec |
| Gaussian Blur | 3.21 Gpixels/sec | 3.74 Gpixels/sec |
| Feature Matching | 0.86 Gpixels/sec | 0.3 Gpixels/sec |
| Stereo Matching | 273.3 Gpixels/sec | 195.6 Gpixels/sec |
| Particle Physics | 8476.3 FPS | 5161.6 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 807 | 848 |
| DirectX 11 | 104 FPS | 99 FPS |
| DirectX 12 | 50 FPS | 49 FPS |
| GPU Compute | 5033 Ops/s | 6123 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce GTX 1660 SUPER
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-03-02 (TEST) | Cinebench 2024 | 3271 |
GeForce GTX 1070
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-08-09 (yourtrain) | Geekbench 6 OpenCL | 53862 |
| 📘 2026-08-09 (yourtrain) | Cinebench 2024 | 3551 |
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) | 4278 | 2295 |
| Image Segmentation (HP) | 5856 | 4955 |
| Image Super Resolution (Q) | 9561 | 10587 |
| Face Detection (HP) | 9830 | 8747 |
| Pose Estimation (Q) | 36109 | 51263 |
| Text Classification (SP) | 1858 | 1461 |
| Machine Translation (HP) | 3286 | 2342 |
| Object Detection (SP) | 5151 | 2960 |
| Depth Estimation (Q) | 18021 | 15275 |
| Style Transfer (SP) | 73708 | 104907 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce GTX 1660 SUPER and GTX 1070General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | October 29, 2019 | January 10, 2016 |
| Launch price (MSRP) | $229 | $379 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Entry-level | Mid-range |
| Architecture | Turing | Pascal |
| GPU Codename | TU116 | GP104 |
| Rival Equivalent | - Radeon RX 5600 XT | - Radeon RX 5600 XT |
| Successor | - | - GeForce RTX 5070 |
| Recommended CPU | - Intel Core i5 9500 or above | - Intel Core i7 7700K or above |
Desktop GPU rating (75th and 76th place)
Graphics Processing Unit
| Base Clock | 1530 MHz | 1506 MHz |
| Boost Clock | 1785 MHz | 1683 MHz |
| Shading Units | 1408 | 1920 |
| Texture Mapping Units (TMUs) | 88 | 120 |
| Render Output Units (ROPs) | 48 | 64 |
| Compute Units (Pipelines) | 22 | 15 |
| Tensor Cores | No | No |
| Ray-tracing Cores | No | No |
| L1 Cache | 64KB per cluster | 48KB per cluster |
| L2 Cache | 1536KB shared | 2MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 86 GPixel/s | 108 GPixel/s |
| Texture Fill Rate | 157 GTexel/s | 202 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| TGP | 125 W | 150 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 12 nm | 16 nm |
| Die Size | 284 mm² | 314 mm² |
| Transistor Count | 6 billion | 7 billion |
| Transistor Density | 21.13 MTr/mm² | 22.29 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR5 |
| Memory Size | 6 GB | 8 GB |
| Memory Clock | 1750 MHz | 2002 MHz |
| Effective Memory Speed | 14000 Mbps | 8000 Mbps |
| Bus | 192-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 | 7.5 | 6.1 |
| Ray Tracing | No | No |
| DLSS | No | No |
| DisplayPort | 1.4a | 1.4a |
Further details
Notes on GTX 1070:
- There's a version with GDDR5X memory.
Cast your vote
Total votes: 159