Product Compare
NVIDIA GeForce RTX 3090 Ti vs NVIDIA RTX PRO 4500 Blackwell Server
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2022 | Mar 2026 |
| Generation | GeForce 30 | Server Blackwell |
| Type | Desktop | Professional |
| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 1560 MHz | 1215 MHz |
| Boost Clock | 1860 MHz | 2415 MHz |
| Memory Clock | 1313 MHz | 1563 MHz |
| Memory | ||
| Memory Size | 24GB | 32GB |
| Memory Type | GDDR6X | GDDR7 |
| Memory Bus | 384bit | 256bit |
| Bandwidth | 1.01TB/s | 800.3GB/s |
| Render Config | ||
| SM Count | 84 | 82 |
| Shading Units | 10752 | 10496 |
| TMUs | 336 | 328 |
| ROPs | 112 | 112 |
| Tensor Cores | 336 | 328 |
| RT Cores | 84 | 82 |
| L1 Cache | 128 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 6 MB | 64 MB |
| Theoretical Performance | ||
| Pixel Rate | 208.3 GPixel/s | 270.5 GPixel/s |
| Texture Rate | 625.0 GTexel/s | 792.1 GTexel/s |
| FP16 (half) | 40.00 TFLOPS | 50.70 TFLOPS |
| FP32 (float) | 40.00 TFLOPS | 50.70 TFLOPS |
| FP64 (double) | 625.0 GFLOPS | 792.1 GFLOPS |
| Graphics Processor | ||
| GPU Name | GA102 | GB203 |
| GPU Variant | GA102-350-A1 | |
| Architecture | Ampere | Blackwell 2.0 |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 5 nm |
| Transistors | 28.3 billion | 45.6 billion |
| Die Size | 628 mm² | 378 mm² |
| Board Design | ||
| TDP | 450W | 165W |
| Suggested PSU | 850 W | 450 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 16-pin | 1x 16-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 | 1.4 |
| CUDA | 8.6 | 12.0 |
| Shader Model | 6.8 | 6.9 |