Flopper.io GPU Comparison Sheet
NVIDIA GB10 Grace Blackwell vs NVIDIA RTX PRO 6000 Blackwell Workstation Edition
Side by side datacenter GPU specifications from the Flopper.io database.
Overview
| NVIDIA GB10 Grace Blackwell | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | |
|---|---|---|
| FP32 TFLOPS | 31.0 | 126.0 |
| Memory | 128 GB | 96 GB |
| Memory Bandwidth | 273 GB/s | 1.8 TB/s |
| TDP | 180 W | 600 W |
Performance by Precision
| Precision | NVIDIA GB10 Grace Blackwell peak TFLOPS (dense) | NVIDIA RTX PRO 6000 Blackwell Workstation Edition peak TFLOPS (dense) |
|---|---|---|
| FP64 | — | 2.0 |
| FP32 | 31.0 | 126.0 |
| TF32 | — | 251.9 |
| BF16 | — | 503.8 |
| FP16 | — | 503.8 |
| FP8 | — | 1007.6 |
| FP6 | — | — |
| FP4 | 500.0 | 2015.2 |
| INT8 | — | 1007.6 |
Specifications
| NVIDIA GB10 Grace Blackwell | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | |
|---|---|---|
| Architecture | Blackwell | Blackwell |
| Process Node | — | 4nm |
| Launch Year | 2025 | 2025 |
| Form Factor | Integrated | PCIe |
| Memory Type | LPDDR5X | GDDR7 |
| Interface Width | — | 512-bit |
| Interconnect | — | — |
| TDP | 180 W | 600 W |
| FP32 Efficiency | 0.17 TFLOPS/W | 0.21 TFLOPS/W |