Estimate resources for AutoML execution
To train an Information Extraction (IE) model on a local desktop or via terminal, your machine needs at least 8 GB RAM and 2 CPU.
The table below lists recommendations on resource utilization for different IE model types:
| Model | RAM | CPU |
|---|---|---|
| Generic IE | 16 GB | 4 |
| Generic Search Engine 2.0 | 8 GB | 4 |
| Generic Binary Classification 1 | 16 GB | 8 |
| Generic Multi-class Classification | 16 GB | 8 |
| Extended Generic IE Search Engine 2.0 or Generic IE | 16 GB | 8 |
1 Estimated for a training set with fewer than 3,000 documents and 6 classes. Exact values depend on the document volume and amount of selected classes.