Peak double precision floating point performance | N/A |
Peak single precision floating point performance | 2.2 TFlops (boost) |
Number of GPU's | 1 |
Cores | 1024 |
Memory size per board (GDDR5) | 4GB GDDR5 |
Memory bandwidth for board (ECC off)
| 88 GB/s |
GPU Computing Applications | Deep learning and inference |
Architecture Features | Deep learning models typically take days to weeks to train, forcing scientists to make compromises between accuracy and time to deployment. The NVIDIA Tesla M4 GPU accelerator, based on the NVIDIA Maxwell |
System | Compatible with HPE ProLiant DL360, and DL380 Gen9 servers |
Product dimensions (H x W x D) | 0.62 x 6.61 x 2.71 in |
Weight | .53 lb |
| |