diff --git a/docs/source/getting_started/gaudi-installation.rst b/docs/source/getting_started/gaudi-installation.rst
index 256c6b401ec10..95e9d6db9331a 100644
--- a/docs/source/getting_started/gaudi-installation.rst
+++ b/docs/source/getting_started/gaudi-installation.rst
@@ -256,7 +256,7 @@ Environment variable ``VLLM_GRAPH_PROMPT_RATIO`` determines the ratio of usable
 Lower value corresponds to less usable graph memory reserved for prefill stage, e.g. ``VLLM_GRAPH_PROMPT_RATIO=0.2`` will reserve 20% of usable graph memory for prefill graphs, and 80% of usable graph memory for decode graphs. 
 
 .. note:: 
-   ``gpu_memory_utilization`` does not correspond to the absolute memory usage across HPU. It describes the memory margin after loading the model and performing a profile run.
+   ``gpu_memory_utilization`` does not correspond to the absolute memory usage across HPU. It specifies the memory margin after loading the model and performing a profile run. If device has 100 GiB of total memory, and 50 GiB of free memory after loading model weights and executing profiling run, ``gpu_memory_utilization`` at its default value will mark 90% of 50 GiB as usable, leaving 5 GiB of margin, regardless of total device memory.   
 
 User can also configure the strategy for capturing HPU Graphs for prompt and decode stages separately. Strategy affects the order of capturing graphs. There are two strategies implemented:
 -    ``max_bs`` - graph capture queue will sorted in descending order by their batch sizes. Buckets with equal batch sizes are sorted by sequence length in ascending order (e.g. ``(64, 128)``, ``(64, 256)``, ``(32, 128)``, ``(32, 256)``, ``(1, 128)``, ``(1,256)``), default strategy for decode