diff --git a/docs/source/tutorials/multi_npu.md b/docs/source/tutorials/multi_npu.md
index c1e5680..e59b725 100644
--- a/docs/source/tutorials/multi_npu.md
+++ b/docs/source/tutorials/multi_npu.md
@@ -30,10 +30,10 @@ docker run --rm \
 Setup environment variables:
 
 ```bash
-# Use Modelscope mirror to speed up model download
+# Load model from ModelScope to speed up download
 export VLLM_USE_MODELSCOPE=True
 
-# To avoid NPU out of memory, set `max_split_size_mb` to any value lower than you need to allocate for Qwen2.5-7B-Instruct
+# Set `max_split_size_mb` to reduce memory fragmentation and avoid out of memory
 export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256
 ```
 
diff --git a/docs/source/tutorials/single_npu.md b/docs/source/tutorials/single_npu.md
index d5bba0a..63e9331 100644
--- a/docs/source/tutorials/single_npu.md
+++ b/docs/source/tutorials/single_npu.md
@@ -29,10 +29,10 @@ docker run --rm \
 Setup environment variables:
 
 ```bash
-# Use Modelscope mirror to speed up model download
+# Load model from ModelScope to speed up download
 export VLLM_USE_MODELSCOPE=True
 
-# To avoid NPU out of memory, set `max_split_size_mb` to any value lower than you need to allocate for Qwen2.5-7B-Instruct
+# Set `max_split_size_mb` to reduce memory fragmentation and avoid out of memory
 export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256
 ```
 
diff --git a/docs/source/tutorials/single_npu_multimodal.md b/docs/source/tutorials/single_npu_multimodal.md
index 2d2d531..c893090 100644
--- a/docs/source/tutorials/single_npu_multimodal.md
+++ b/docs/source/tutorials/single_npu_multimodal.md
@@ -29,10 +29,10 @@ docker run --rm \
 Setup environment variables:
 
 ```bash
-# Use Modelscope mirror to speed up model download
+# Load model from ModelScope to speed up download
 export VLLM_USE_MODELSCOPE=True
 
-# To avoid NPU out of memory, set `max_split_size_mb` to any value lower than you need to allocate for Qwen2.5-7B-Instruct
+# Set `max_split_size_mb` to reduce memory fragmentation and avoid out of memory
 export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256
 ```