diff --git a/pkgs/by-name/ll/llama-cpp/disable_bfloat16.patch b/pkgs/by-name/ll/llama-cpp/disable_bfloat16.patch
deleted file mode 100644
index 38388e2b82dc..000000000000
--- a/pkgs/by-name/ll/llama-cpp/disable_bfloat16.patch
+++ /dev/null
@@ -1,15 +0,0 @@
-index b97e7bf9..9cdc62a4 100644
---- a/ggml/src/ggml-vulkan/CMakeLists.txt
-+++ b/ggml/src/ggml-vulkan/CMakeLists.txt
-@@ -70,11 +70,5 @@ if (Vulkan_FOUND)
-         "GGML_VULKAN_INTEGER_DOT_GLSLC_SUPPORT"
-     )
-
--    test_shader_extension_support(
--        "GL_EXT_bfloat16"
--        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_bfloat16_support.comp"
--        "GGML_VULKAN_BFLOAT16_GLSLC_SUPPORT"
--    )
--
-     target_link_libraries(ggml-vulkan PRIVATE Vulkan::Vulkan)
-     target_include_directories(ggml-vulkan PRIVATE ${CMAKE_CURRENT_BINARY_DIR})
diff --git a/pkgs/by-name/ll/llama-cpp/package.nix b/pkgs/by-name/ll/llama-cpp/package.nix
index 4fd8d35ddd6f..9df32043c859 100644
--- a/pkgs/by-name/ll/llama-cpp/package.nix
+++ b/pkgs/by-name/ll/llama-cpp/package.nix
@@ -75,13 +75,13 @@ let
 in
 effectiveStdenv.mkDerivation (finalAttrs: {
   pname = "llama-cpp";
-  version = "6670";
+  version = "6729";
 
   src = fetchFromGitHub {
     owner = "ggml-org";
     repo = "llama.cpp";
     tag = "b${finalAttrs.version}";
-    hash = "sha256-B4Qog7RLcre8KB9N+aVUZSJwlkHIIcCxR8jySoxbXoQ=";
+    hash = "sha256-CkPLgzSsiCkSIAp4XetUJszt0+WjPRt+9V9SvRogbVU=";
     leaveDotGit = true;
     postFetch = ''
       git -C "$out" rev-parse --short HEAD > $out/COMMIT
@@ -89,8 +89,6 @@ effectiveStdenv.mkDerivation (finalAttrs: {
     '';
   };
 
-  patches = lib.optionals vulkanSupport [ ./disable_bfloat16.patch ];
-
   nativeBuildInputs = [
     cmake
     ninja