Product Compare
NVIDIA B300 vs NVIDIA RTX A2000 Max-Q 8 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Sep 2025 | Apr 2021 |
| Generation | Server Blackwell | Ampere-MW |
| Type | Desktop | Mobile |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1665 MHz | 607 MHz |
| Boost Clock | 2032 MHz | 1177 MHz |
| Memory Clock | 2000 MHz | 1375 MHz |
| Memory | ||
| Memory Size | 144GB | 8GB |
| Memory Type | HBM3e | GDDR6 |
| Memory Bus | 4096bit | 128bit |
| Bandwidth | 4.10TB/s | 176.0GB/s |
| Render Config | ||
| SM Count | 148 | 20 |
| Shading Units | 18944 | 2560 |
| TMUs | 592 | 80 |
| ROPs | 24 | 48 |
| Tensor Cores | 592 | 80 |
| L1 Cache | 256 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 50 MB | 2 MB |
| RT Cores | 20 | |
| Theoretical Performance | ||
| Pixel Rate | 48.77 GPixel/s | 56.50 GPixel/s |
| Texture Rate | 1202.9 GTexel/s | 94.16 GTexel/s |
| FP16 (half) | 1231.8 TFLOPS | 6.026 TFLOPS |
| FP32 (float) | 76.99 TFLOPS | 6.026 TFLOPS |
| FP64 (double) | 1202.9 GFLOPS | 94.16 GFLOPS |
| Graphics Processor | ||
| GPU Name | GB110 | GA107 |
| Architecture | Blackwell Ultra | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 5 nm | 8 nm |
| Transistors | 104 billion | 8.7 billion |
| Die Size | Unknown | 200 mm² |
| Board Design | ||
| TDP | 1400W | 95W |
| Suggested PSU | 1800 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 | 10.3 | 8.6 |
| Shader Model | N/A | 6.8 |