diff --git a/backend/README.md b/backend/README.md
index c1fe7af..3e13298 100644
--- a/backend/README.md
+++ b/backend/README.md
@@ -5,7 +5,7 @@ Below will setup the backend including the `go` orchestration layer
 and a `llama.cpp` inference server on `localhost:8081` and
 `localhost:8080` for local testing.
 ### Building `llama.cpp`
-In `$REPO/third_party/llama.cpp` run `make` to build.
+See documentation for `llama.cpp` for details.
 
 ### Running `llama.cpp`
 #### Getting a `GGUF` format model