GeForce RTX 4060 vs GeForce RTX 3070
Summary
Reasons to consider GeForce RTX 4060 |
Higher theoretical gaming performance, based on specifications. |
Reasons to consider GeForce RTX 3070 |
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) |
HWBench recommends GeForce RTX 4060
Based on theoretical specifications.
Core Configuration
| GeForce RTX 4060 | | GeForce RTX 3070 | |
---|
GPU Name | AD104 () | vs | GA104 (GA104-300-A1) |
Fab Process | 4 nm | vs | 8 nm |
Die Size | 295 mm² | vs | 392 mm² |
Transistors | 35,800 million | vs | 17,400 million |
Shaders | 5888 | vs | 5888 |
Tensor Cores | 184 | vs | none |
Raytracing Cores | 46 | vs | none |
Compute Units | 46 | vs | 46 |
Core clock | 2505 MHz | vs | 1500 MHz |
ROPs | 64 | vs | 64 |
TMUs | 184 | vs | 184 |
Memory Configuration
| GeForce RTX 4060 | | GeForce RTX 3070 | |
---|
Memory Type | GDDR6 | vs | GDDR6 |
Bus Width | 128 bit | vs | 256 bit |
Memory Speed | 2250 MHz
18 Gbps effective | vs | 1750 MHz
14 Gbps effective |
Memory Size | 8192 Mb | vs | 8192 Mb |
Additional details
| GeForce RTX 4060 | | GeForce RTX 3070 | |
---|
TDP | 200 watts | vs | 220 watts |
Release Date | UNRELEASED | vs | 1 Sep 2020 |
GeForce RTX 4060
169.00 GP/s
GeForce RTX 3070
110.40 GP/s
GigaPixels - higher is better
GeForce RTX 4060
485.80 GT/s
GeForce RTX 3070
317.40 GT/s
GigaTexels - higher is better
GeForce RTX 4060
288.00 GB/s
GeForce RTX 3070
448.00 GB/s
GB/s - higher is better
GeForce RTX 4060
31090.00 GFLOPs
GeForce RTX 3070
20310.00 GFLOPs
GFLOPs - higher is better