Select the **Inference Device** : CPU or GPU you want to use for Inference.
_Note: For most of the models generated with the ML-Agents toolkit, CPU will be faster than GPU. Only use GPU if you have a large number of agents using visual observations._
**Note:** For most of the models generated with the ML-Agents toolkit, CPU will be faster than GPU.
You should use the GPU only if you use the
ResNet visual encoder or have a large number of agents with visual observations.