GeForce RTX 3050 Ti vs GeForce GTX 670
Summary
Reasons to consider GeForce RTX 3050 Ti |
| Higher theoretical gaming performance, based on specifications. |
| Supports PhysX |
| Supports G-Sync |
| Supports ShadowPlay (allows game streaming/recording with minimum performance penalty) |
| Supports Direct3D 12 Async Compute |
| Supports DirectX Raytracing (DXR) |
| Supports Deep Learning Super-Sampling (DLSS) |
Reasons to consider GeForce GTX 670 |
| Supports PhysX |
| Supports G-Sync |
| Supports ShadowPlay (allows game streaming/recording with minimum performance penalty) |
| Based on an outdated architecture (Nvidia Kepler), there are less performance optimizations for current games and applications |
HWBench recommends GeForce RTX 3050 Ti
Based on theoretical specifications.
Core Configuration
| GeForce RTX 3050 Ti | | GeForce GTX 670 | |
|---|
| GPU Name | GA106 (GA106-200-A1) | vs | GK104 (GK104-325-A2) |
| Fab Process | 8 nm | vs | 28 nm |
| Die Size | 300 mm² | vs | 294 mm² |
| Transistors | 13,250 million | vs | 3,540 million |
| Shaders | 3584 | vs | 1344 |
| Compute Units | 28 | vs | 7 |
| Core clock | 1350 MHz | vs | 915 MHz |
| ROPs | 64 | vs | 32 |
| TMUs | 112 | vs | 112 |
Memory Configuration
| GeForce RTX 3050 Ti | | GeForce GTX 670 | |
|---|
| Memory Type | GDDR6 | vs | GDDR5 |
| Bus Width | 192 bit | vs | 256 bit |
| Memory Speed | 1750 MHz
14 Gbps effective | vs | 1502 MHz
6008 MHz effective |
| Memory Size | 6144 Mb | vs | 2048 Mb |
Additional details
| GeForce RTX 3050 Ti | | GeForce GTX 670 | |
|---|
| TDP | 150 watts | vs | 170 watts |
| Release Date | UNRELEASED | vs | 10 May 2012 |
GeForce RTX 3050 Ti
108.00 GP/s
GeForce GTX 670
25.60 GP/s
GigaPixels - higher is better
GeForce RTX 3050 Ti
188.90 GT/s
GeForce GTX 670
102.00 GT/s
GigaTexels - higher is better
GeForce RTX 3050 Ti
336.00 GB/s
GeForce GTX 670
192.00 GB/s
GB/s - higher is better
GeForce RTX 3050 Ti
12090.00 GFLOPs
GeForce GTX 670
2460.00 GFLOPs
GFLOPs - higher is better