Product Compare
NVIDIA GeForce RTX 4080 16 GB vs NVIDIA Rubin Ultra GPU
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Sep 2022 | Jan 2027 |
| Generation | GeForce 40 | Server Rubin |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 4.0 x16 | PCIe 6.0 x16 |
| Clock Speeds | ||
| Base Clock | 2205 MHz | 700 MHz |
| Boost Clock | 2505 MHz | 2267 MHz |
| Memory Clock | 1400 MHz | 1900 MHz |
| Memory | ||
| Memory Size | 16GB | 1024GB |
| Memory Type | GDDR6X | HBM4e |
| Memory Bus | 256bit | 32768bit |
| Bandwidth | 716.8GB/s | 31.1TB/s |
| Render Config | ||
| SM Count | 76 | 448 |
| Shading Units | 9728 | 57344 |
| TMUs | 304 | 1792 |
| ROPs | 112 | 24 |
| Tensor Cores | 304 | 1792 |
| RT Cores | 76 | |
| L1 Cache | 128 KB (per SM) | 256 KB (per SM) |
| L2 Cache | 64 MB | 128 MB |
| Theoretical Performance | ||
| Pixel Rate | 280.6 GPixel/s | 54.41 GPixel/s |
| Texture Rate | 761.5 GTexel/s | 4062.5 GTexel/s |
| FP16 (half) | 48.74 TFLOPS | 520.0 TFLOPS |
| FP32 (float) | 48.74 TFLOPS | 260.0 TFLOPS |
| FP64 (double) | 761.5 GFLOPS | 65.00 TFLOPS |
| Graphics Processor | ||
| GPU Name | AD103 | GR110 |
| GPU Variant | AD103-300-A1 | |
| Architecture | Ada Lovelace | Rubin Ultra |
| Foundry | TSMC | TSMC |
| Process Size | 4 nm | 3 nm |
| Transistors | 45.9 billion | 670 billion |
| Die Size | 379 mm² | 2912 mm² |
| Board Design | ||
| TDP | 320W | 3600W |
| Suggested PSU | 700 W | 4000 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 16-pin | |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 8.9 | 10.7 |
| Shader Model | 6.6 | N/A |