Product Compare
NVIDIA GeForce RTX 4070 vs NVIDIA GeForce RTX 3080 Ti
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Apr 2023 | May 2021 |
| Generation | GeForce 40 | GeForce 30 |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1920 MHz | 1365 MHz |
| Boost Clock | 2475 MHz | 1665 MHz |
| Memory Clock | 1313 MHz | 1188 MHz |
| Memory | ||
| Memory Size | 12GB | 12GB |
| Memory Type | GDDR6X | GDDR6X |
| Memory Bus | 192bit | 384bit |
| Bandwidth | 504.2GB/s | 912.4GB/s |
| Render Config | ||
| SM Count | 46 | 80 |
| Shading Units | 5888 | 10240 |
| TMUs | 184 | 320 |
| ROPs | 64 | 112 |
| Tensor Cores | 184 | 320 |
| RT Cores | 46 | 80 |
| L1 Cache | 128 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 36 MB | 6 MB |
| Theoretical Performance | ||
| Pixel Rate | 158.4 GPixel/s | 186.5 GPixel/s |
| Texture Rate | 455.4 GTexel/s | 532.8 GTexel/s |
| FP16 (half) | 29.15 TFLOPS | 34.10 TFLOPS |
| FP32 (float) | 29.15 TFLOPS | 34.10 TFLOPS |
| FP64 (double) | 455.4 GFLOPS | 532.8 GFLOPS |
| Graphics Processor | ||
| GPU Name | AD104 | GA102 |
| GPU Variant | AD104-250-A1 | GA102-225-A1 |
| Architecture | Ada Lovelace | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 5 nm | 8 nm |
| Transistors | 35.8 billion | 28.3 billion |
| Die Size | 295 mm² | 628 mm² |
| Board Design | ||
| TDP | 200W | 350W |
| Suggested PSU | 550 W | 750 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | 1x HDMI 2.13x DisplayPort 1.4a |
| Power Connectors | 1x 16-pin | 1x 12-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 8.9 | 8.6 |
| Shader Model | 6.7 | 6.6 |
| Benchmarks | ||
| 3DMark Time Spy | 17887 | 19629 |
| 3DMark Time Spy Extreme | 7907 | 10032 |
| 3DMark Speed Way | 5508 | 5330 |