Flopper.io GPU Comparison Sheet
Huawei Ascend 910B vs NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
Side by side datacenter GPU specifications from the Flopper.io database.
Overview
| Huawei Ascend 910B | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | |
|---|---|---|
| FP32 TFLOPS | — | 109.7 |
| Memory | 64 GB | 96 GB |
| Memory Bandwidth | 1.6 TB/s | 1.8 TB/s |
| TDP | 400 W | 300 W |
Performance by Precision
| Precision | Huawei Ascend 910B peak TFLOPS (dense) | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition peak TFLOPS (dense) |
|---|---|---|
| FP64 | — | 1.7 |
| FP32 | — | 109.7 |
| TF32 | — | 219.5 |
| BF16 | 400.0 | 438.9 |
| FP16 | 400.0 | 438.9 |
| FP8 | — | 877.9 |
| FP6 | — | — |
| FP4 | — | 1755.7 |
| INT8 | 800.0 | 877.9 |
Specifications
| Huawei Ascend 910B | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | |
|---|---|---|
| Architecture | Da Vinci v2 | Blackwell |
| Process Node | SMIC 7nm | 4nm |
| Launch Year | 2024 | 2025 |
| Form Factor | OAM | PCIe |
| Memory Type | HBM2e | GDDR7 |
| Interface Width | — | 512-bit |
| Interconnect | HCCS | — |
| TDP | 400 W | 300 W |
| FP32 Efficiency | — | 0.37 TFLOPS/W |