docs: update README.md

README.md

@@ -136,7 +136,7 @@ pip install 'vllm>=0.15.0'
 ```
 See [its documentation](https://docs.vllm.ai/en/stable/getting_started/installation/index.html) for more details.
 
-The following command can be used to create an API endpoint at `http://localhost:8000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
+The following command can be used to create an API endpoint at `http://localhost:8000/v1` with maximum context length 256K tokens using tensor parallel on 2 GPUs.
 ```shell
 vllm serve Qwen/Qwen3-Coder-Next-FP8 --port 8000 --tensor-parallel-size 2 --enable-auto-tool-choice --tool-call-parser qwen3_coder
 ```