Product Compare
NVIDIA B200 SXM 192 GB vs NVIDIA GeForce RTX 3050 Max-Q Refresh 6 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2024 | Jul 2022 |
| Generation | Server Blackwell | GeForce 30 Mobile |
| Type | Desktop | Mobile |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x8 |
| Clock Speeds | ||
| Base Clock | 1665 MHz | 622 MHz |
| Boost Clock | 1837 MHz | 990 MHz |
| Memory Clock | 2000 MHz | 1500 MHz |
| Memory | ||
| Memory Size | 96GB | 6GB |
| Memory Type | HBM3e | GDDR6 |
| Memory Bus | 4096bit | 96bit |
| Bandwidth | 4.10TB/s | 144.0GB/s |
| Render Config | ||
| SM Count | 132 | 16 |
| Shading Units | 16896 | 2048 |
| TMUs | 528 | 64 |
| ROPs | 24 | 32 |
| Tensor Cores | 528 | 64 |
| L1 Cache | 256 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 50 MB | 2 MB |
| RT Cores | 16 | |
| Theoretical Performance | ||
| Pixel Rate | 44.09 GPixel/s | 31.68 GPixel/s |
| Texture Rate | 969.9 GTexel/s | 63.36 GTexel/s |
| FP16 (half) | 248.3 TFLOPS | 4.055 TFLOPS |
| FP32 (float) | 62.08 TFLOPS | 4.055 TFLOPS |
| FP64 (double) | 31.04 TFLOPS | 63.36 GFLOPS |
| Graphics Processor | ||
| GPU Name | GB100 | GA107 |
| Architecture | Blackwell | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 5 nm | 8 nm |
| Transistors | 104 billion | 8.7 billion |
| Die Size | Unknown | 200 mm² |
| Board Design | ||
| TDP | 1000W | 35W |
| Suggested PSU | 1400 W | |
| Outputs | No outputs | Portable Device Dependent |
| Power Connectors | None | |
| Graphics Features | ||
| DirectX | N/A | 12 Ultimate (12_2) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | 10.0 | 8.6 |
| Shader Model | N/A | 6.7 |