diff --git a/docs/getting-started/quick-start/starting-with-openai-compatible.mdx b/docs/getting-started/quick-start/starting-with-openai-compatible.mdx
index aba3f79..5710634 100644
--- a/docs/getting-started/quick-start/starting-with-openai-compatible.mdx
+++ b/docs/getting-started/quick-start/starting-with-openai-compatible.mdx
@@ -20,7 +20,7 @@ There are many servers and tools that expose an OpenAI-compatible API. Here are
 - [Llama.cpp](https://github.com/ggml-org/llama.cpp): Extremely efficient, runs on CPU and GPU
 - [Ollama](https://ollama.com/): Super user-friendly and cross-platform
 - [LM Studio](https://lmstudio.ai/): Rich desktop app for Windows/Mac/Linux
-- [Lemonade (ONNX TurnkeyML)](https://github.com/onnx/turnkeyml): Fast ONNX-based backend, easily runs GGUF and other models locally
+- [Lemonade (ONNX TurnkeyML)](https://github.com/onnx/turnkeyml): Fast ONNX-based backend with NPU/iGPU acceleration
 
 Pick whichever suits your workflow!
 
@@ -41,8 +41,7 @@ Lemonade is a plug-and-play ONNX-based OpenAI-compatible server. Here’s how to
 
 ![Lemonade Server](/images/getting-started/lemonade-server.png)
 
-
-Lemonade works on Linux and Mac too—see [their docs](https://github.com/onnx/turnkeyml) for details.
+See [their docs](https://github.com/onnx/turnkeyml) for details.
 
 ---