diff --git a/README.md b/README.md
index 2f167fa..b7ca4bb 100644
--- a/README.md
+++ b/README.md
@@ -107,9 +107,8 @@ We will switch to our model, this will significantly save on inference time.
 1. Install [docker](https://docs.docker.com/engine/install/)
 2. Run any terminal. It is required to get the prediction probability
 3. Place a single CT scan in dicom-format into a folder
-4. CPU: `docker run -it --rm -v <path to a CT folder>:/app/perdict _______`
+4. CPU: `docker run -it --rm -v <path to a CT folder>:/app/perdict _______`  (very slow: 10-15 mins)
 5. GPU: `docker run --gpus 'device=0' -it --rm -v <path to a CT folder>:/app/perdict _______`
-6.  Wait about 10-15 mins
 7.  Final line in the container output is the probability of having cancer. (0 - cancer-free, 1 - positive)
 
 Container size is huge (~21 GB). It will take sometime to pull it from registry.