Product Compare
NVIDIA Tesla M10 vs NVIDIA B200 SXM6
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | May 2016 | Nov 2024 |
| Generation | Tesla | Server Blackwell |
| Type | Professional | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 6.0 x16 |
| Clock Speeds | ||
| Base Clock | 1033 MHz | 120 MHz |
| Boost Clock | 1306 MHz | 1830 MHz |
| Memory Clock | 1300 MHz | 2000 MHz |
| Memory | ||
| Memory Size | 8GB | 180GB |
| Memory Type | GDDR5 | HBM3e |
| Memory Bus | 128bit | 8192bit |
| Bandwidth | 83.20GB/s | 8.19TB/s |
| Render Config | ||
| Shading Units | 640 | 18944 |
| TMUs | 40 | 592 |
| ROPs | 16 | 24 |
| L1 Cache | 64 KB (per SMM) | 256 KB (per SM) |
| L2 Cache | 2 MB | 126 MB |
| SM Count | 148 | |
| Tensor Cores | 592 | |
| Theoretical Performance | ||
| Pixel Rate | 20.90 GPixel/s | 43.92 GPixel/s |
| Texture Rate | 52.24 GTexel/s | 1083.4 GTexel/s |
| FP32 (float) | 1.672 TFLOPS | 69.34 TFLOPS |
| FP64 (double) | 52.24 GFLOPS | 34.67 TFLOPS |
| FP16 (half) | 1109.4 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GM107 | GB100 |
| GPU Variant | GM107-570-A2 | GB100-886N-A1 |
| Architecture | Maxwell | Blackwell |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 5 nm |
| Transistors | 1.87 billion | 208 billion |
| Die Size | 148 mm² | 1628 mm² |
| Board Design | ||
| TDP | 225W | 1000W |
| Suggested PSU | 550 W | 1400 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 1x 8-pin | |
| Graphics Features | ||
| DirectX | 12 (11_0) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 5.0 | 10.0 |
| Shader Model | 5.1 | N/A |