diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
index dcc65f02..1a990306 100644
--- a/examples/llava/clip.cpp
+++ b/examples/llava/clip.cpp
@@ -66,6 +66,19 @@
 #include <cinttypes>
 #include <limits>
 
+#if defined(_WIN32)
+#define WIN32_LEAN_AND_MEAN
+#ifndef NOMINMAX
+    #define NOMINMAX
+#endif
+#include <windows.h>
+#if __GLIBCXX__
+#include <cstdio>
+#include <ext/stdio_filebuf.h>
+#include <fcntl.h>
+#endif
+#endif
+
 //#define CLIP_DEBUG_FUNCTIONS
 
 // RGB uint8 image
@@ -1248,7 +1261,29 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
             return nullptr;
         }
 
+#ifdef _WIN32
+        int wlen = MultiByteToWideChar(CP_UTF8, 0, fname, -1, NULL, 0);
+        if (!wlen) {
+            return NULL;
+        }
+        wchar_t * wbuf = (wchar_t *) malloc(wlen * sizeof(wchar_t));
+        wlen = MultiByteToWideChar(CP_UTF8, 0, fname, -1, wbuf, wlen);
+        if (!wlen) {
+            free(wbuf);
+            return NULL;
+        }
+#if __GLIBCXX__
+        int fd = _wopen(wbuf, _O_RDONLY | _O_BINARY);
+        __gnu_cxx::stdio_filebuf<char> buffer(fd, std::ios_base::in);
+        std::istream fin(&buffer);
+#else // MSVC
+        // unused in our current build
+        auto fin = std::ifstream(wbuf, std::ios::binary);
+#endif
+        free(wbuf);
+#else
         auto fin = std::ifstream(fname, std::ios::binary);
+#endif
         if (!fin) {
             LOG_TEE("cannot open model file for loading tensors\n");
             clip_free(new_clip);
@@ -1288,7 +1323,11 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
                 ggml_backend_tensor_set(cur, read_buf.data(), 0, num_bytes);
             }
         }
+#if defined(_WIN32) && defined(__GLIBCXX__)
+        close(fd);
+#else
         fin.close();
+#endif
     }
 
     // vision model