diff --git a/README.md b/README.md
index 9f2f8df64..ecbe802df 100644
--- a/README.md
+++ b/README.md
@@ -532,7 +532,7 @@ Building the program with BLAS support may lead to some performance improvements
         cmake -B build -DLLAMA_HIPBLAS=ON -DAMDGPU_TARGETS=gfx1030 -DCMAKE_BUILD_TYPE=Release \
         && cmake --build build --config Release -- -j 16
     ```
-    On Linux it is also possible to use unified memory architecture (UMA) to share main memory between the CPU and integrated GPU by setting `-DLLAMA_HIP_UMA=ON"`.
+    On Linux it is also possible to use unified memory architecture (UMA) to share main memory between the CPU and integrated GPU by setting `-DLLAMA_HIP_UMA=ON`.
     However, this hurts performance for non-integrated GPUs (but enables working with integrated GPUs).
 
   - Using `make` (example for target gfx1030, build with 16 CPU threads):