Product Compare
NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 2060 TU104
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2022 | Jan 2020 |
| Generation | GeForce 30 | GeForce 20 |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 1560 MHz | 1365 MHz |
| Boost Clock | 1860 MHz | 1680 MHz |
| Memory Clock | 1313 MHz | 1750 MHz |
| Memory | ||
| Memory Size | 24GB | 6GB |
| Memory Type | GDDR6X | GDDR6 |
| Memory Bus | 384bit | 192bit |
| Bandwidth | 1.01TB/s | 336.0GB/s |
| Render Config | ||
| SM Count | 84 | 30 |
| Shading Units | 10752 | 1920 |
| TMUs | 336 | 120 |
| ROPs | 112 | 48 |
| Tensor Cores | 336 | 240 |
| RT Cores | 84 | 30 |
| L1 Cache | 128 KB (per SM) | 64 KB (per SM) |
| L2 Cache | 6 MB | 3 MB |
| Theoretical Performance | ||
| Pixel Rate | 208.3 GPixel/s | 80.64 GPixel/s |
| Texture Rate | 625.0 GTexel/s | 201.6 GTexel/s |
| FP16 (half) | 40.00 TFLOPS | 12.90 TFLOPS |
| FP32 (float) | 40.00 TFLOPS | 6.451 TFLOPS |
| FP64 (double) | 625.0 GFLOPS | 201.6 GFLOPS |
| Graphics Processor | ||
| GPU Name | GA102 | TU104 |
| GPU Variant | GA102-350-A1 | TU104-150-KC-A1 |
| Architecture | Ampere | Turing |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 12 nm |
| Transistors | 28.3 billion | 13.6 billion |
| Die Size | 628 mm² | 545 mm² |
| Board Design | ||
| TDP | 450W | 160W |
| Suggested PSU | 850 W | 450 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | 1x DVI1x HDMI 2.02x DisplayPort 1.4a1x USB Type-C |
| Power Connectors | 1x 16-pin | 1x 8-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | 1.3 |
| CUDA | 8.6 | 7.5 |
| Shader Model | 6.8 | 6.6 |