diff --git a/.devops/nix/package.nix b/.devops/nix/package.nix
index 79a7270e5d..289273e72e 100644
--- a/.devops/nix/package.nix
+++ b/.devops/nix/package.nix
@@ -41,6 +41,7 @@
   effectiveStdenv ? if useCuda then cudaPackages.backendStdenv else stdenv,
   enableStatic ? effectiveStdenv.hostPlatform.isStatic,
   precompileMetalShaders ? false,
+  useWebUi ? true,
 }:
 
 let
@@ -164,6 +165,7 @@ effectiveStdenv.mkDerivation (finalAttrs: {
   cmakeFlags =
     [
       (cmakeBool "LLAMA_BUILD_SERVER" true)
+      (cmakeBool "LLAMA_BUILD_WEBUI" useWebUi)
       (cmakeBool "BUILD_SHARED_LIBS" (!enableStatic))
       (cmakeBool "CMAKE_SKIP_BUILD_RPATH" true)
       (cmakeBool "GGML_NATIVE" false)
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 69da97dc1e..caea48c506 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -108,6 +108,7 @@ option(LLAMA_BUILD_TESTS    "llama: build tests"          ${LLAMA_STANDALONE})
 option(LLAMA_BUILD_TOOLS    "llama: build tools"          ${LLAMA_STANDALONE})
 option(LLAMA_BUILD_EXAMPLES "llama: build examples"       ${LLAMA_STANDALONE})
 option(LLAMA_BUILD_SERVER   "llama: build server example" ${LLAMA_STANDALONE})
+option(LLAMA_BUILD_WEBUI    "llama: build the embedded Web UI for server"  ON)
 option(LLAMA_TOOLS_INSTALL  "llama: install tools"        ${LLAMA_TOOLS_INSTALL_DEFAULT})
 option(LLAMA_TESTS_INSTALL  "llama: install tests"        ON)
 
diff --git a/tools/server/CMakeLists.txt b/tools/server/CMakeLists.txt
index 5621a51b22..02432efbb9 100644
--- a/tools/server/CMakeLists.txt
+++ b/tools/server/CMakeLists.txt
@@ -35,22 +35,29 @@ set(TARGET_SRCS
     server-models.cpp
     server-models.h
 )
-set(PUBLIC_ASSETS
-    index.html.gz
-    loading.html
-)
 
-foreach(asset ${PUBLIC_ASSETS})
-    set(input "${CMAKE_CURRENT_SOURCE_DIR}/public/${asset}")
-    set(output "${CMAKE_CURRENT_BINARY_DIR}/${asset}.hpp")
-    list(APPEND TARGET_SRCS ${output})
-    add_custom_command(
-        DEPENDS "${input}"
-        OUTPUT "${output}"
-        COMMAND "${CMAKE_COMMAND}" "-DINPUT=${input}" "-DOUTPUT=${output}" -P "${PROJECT_SOURCE_DIR}/scripts/xxd.cmake"
+option(LLAMA_BUILD_WEBUI "Build the embedded Web UI" ON)
+
+if (LLAMA_BUILD_WEBUI)
+    set(PUBLIC_ASSETS
+        index.html.gz
+        loading.html
     )
-    set_source_files_properties(${output} PROPERTIES GENERATED TRUE)
-endforeach()
+
+    foreach(asset ${PUBLIC_ASSETS})
+        set(input "${CMAKE_CURRENT_SOURCE_DIR}/public/${asset}")
+        set(output "${CMAKE_CURRENT_BINARY_DIR}/${asset}.hpp")
+        list(APPEND TARGET_SRCS ${output})
+        add_custom_command(
+            DEPENDS "${input}"
+            OUTPUT "${output}"
+            COMMAND "${CMAKE_COMMAND}" "-DINPUT=${input}" "-DOUTPUT=${output}" -P "${PROJECT_SOURCE_DIR}/scripts/xxd.cmake"
+        )
+        set_source_files_properties(${output} PROPERTIES GENERATED TRUE)
+    endforeach()
+    add_definitions(-DLLAMA_BUILD_WEBUI)
+else()
+endif()
 
 add_executable(${TARGET} ${TARGET_SRCS})
 install(TARGETS ${TARGET} RUNTIME)
diff --git a/tools/server/server-http.cpp b/tools/server/server-http.cpp
index 3466512d0c..429cddcc2e 100644
--- a/tools/server/server-http.cpp
+++ b/tools/server/server-http.cpp
@@ -8,9 +8,11 @@
 #include <string>
 #include <thread>
 
+#ifdef LLAMA_BUILD_WEBUI
 // auto generated files (see README.md for details)
 #include "index.html.gz.hpp"
 #include "loading.html.hpp"
+#endif
 
 //
 // HTTP implementation using cpp-httplib
@@ -181,11 +183,14 @@ bool server_http_context::init(const common_params & params) {
     auto middleware_server_state = [this](const httplib::Request & req, httplib::Response & res) {
         bool ready = is_ready.load();
         if (!ready) {
+#ifdef LLAMA_BUILD_WEBUI
             auto tmp = string_split<std::string>(req.path, '.');
             if (req.path == "/" || tmp.back() == "html") {
                 res.status = 503;
                 res.set_content(reinterpret_cast<const char*>(loading_html), loading_html_len, "text/html; charset=utf-8");
-            } else {
+            } else
+#endif
+            {
                 // no endpoints is allowed to be accessed when the server is not ready
                 // this is to prevent any data races or inconsistent states
                 res.status = 503;
@@ -255,6 +260,7 @@ bool server_http_context::init(const common_params & params) {
                 return 1;
             }
         } else {
+#ifdef LLAMA_BUILD_WEBUI
             // using embedded static index.html
             srv->Get(params.api_prefix + "/", [](const httplib::Request & req, httplib::Response & res) {
                 if (req.get_header_value("Accept-Encoding").find("gzip") == std::string::npos) {
@@ -268,6 +274,7 @@ bool server_http_context::init(const common_params & params) {
                 }
                 return false;
             });
+#endif
         }
     }
     return true;