diff --git a/tools/mtmd/README.md b/tools/mtmd/README.md
index ef31d1957cd..154d0c376ae 100644
--- a/tools/mtmd/README.md
+++ b/tools/mtmd/README.md
@@ -37,6 +37,37 @@ Built upon `clip.cpp` (similar to `llava.cpp`), `libmtmd` offers several advanta
 - **Improved UX/DX:** Features a more intuitive API, inspired by the `Processor` class in the Hugging Face `transformers` library.
 - **Flexibility:** Designed to support multiple input types (text, audio, images) while respecting the wide variety of chat templates used by different models.
 
+## Logging Configuration
+
+By default, `libmtmd` logs messages directly to stderr. To integrate `libmtmd` logging with your application's logging system, you can use the `mtmd_log_set_llama_callback()` function to redirect all mtmd/clip logs through llama's logging callback.
+
+**Example usage:**
+
+```c
+#include "llama.h"
+#include "mtmd.h"
+
+// Your custom logging callback
+void my_log_callback(ggml_log_level level, const char * text, void * user_data) {
+    // Your logging logic here
+    printf("[%d] %s", level, text);
+}
+
+int main() {
+    // Set up llama's logging
+    llama_log_set(my_log_callback, NULL);
+    
+    // Redirect mtmd/clip logging to use the same callback
+    mtmd_log_set_llama_callback(my_log_callback, NULL);
+    
+    // Now all mtmd and clip logs will use your custom callback
+    mtmd_context * ctx = mtmd_init_from_file(...);
+    // ...
+}
+```
+
+This ensures that all logging from `libmtmd`, including the underlying `clip.cpp` vision encoder, is routed through your application's logging system consistently.
+
 ## How to obtain `mmproj`
 
 Multimodal projector (`mmproj`) files are specific to each model architecture.
diff --git a/tools/mtmd/clip-impl.h b/tools/mtmd/clip-impl.h
index 664b0c9ac6e..9f2dda7b166 100644
--- a/tools/mtmd/clip-impl.h
+++ b/tools/mtmd/clip-impl.h
@@ -207,6 +207,13 @@ struct clip_logger_state {
 
 extern struct clip_logger_state g_logger_state;
 
+// Function to set logging callback (can be used to redirect to llama's logging)
+// If not called, will use the default callback (logs to stderr)
+static inline void clip_log_set_callback(ggml_log_callback callback, void * user_data) {
+    g_logger_state.log_callback = callback;
+    g_logger_state.log_callback_user_data = user_data;
+}
+
 static void clip_log_internal_v(enum ggml_log_level level, const char * format, va_list args) {
     if (format == NULL) {
         return;
diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp
index e7c516d2de8..f0506a11cef 100644
--- a/tools/mtmd/clip.cpp
+++ b/tools/mtmd/clip.cpp
@@ -28,7 +28,11 @@
 #include <numeric>
 #include <functional>
 
-struct clip_logger_state g_logger_state = {GGML_LOG_LEVEL_CONT, clip_log_callback_default, NULL};
+struct clip_logger_state g_logger_state = {
+    GGML_LOG_LEVEL_CONT,           // verbosity_thold
+    clip_log_callback_default,     // log_callback
+    NULL                           // log_callback_user_data
+};
 
 enum ffn_op_type {
     FFN_GELU,
diff --git a/tools/mtmd/mtmd.cpp b/tools/mtmd/mtmd.cpp
index cd022c5e245..6708bc519e0 100644
--- a/tools/mtmd/mtmd.cpp
+++ b/tools/mtmd/mtmd.cpp
@@ -363,6 +363,10 @@ void mtmd_free(mtmd_context * ctx) {
     }
 }
 
+void mtmd_log_set_llama_callback(ggml_log_callback llama_cb, void * llama_user_data) {
+    clip_log_set_callback(llama_cb, llama_user_data);
+}
+
 struct mtmd_tokenizer {
     mtmd_context * ctx;
     std::vector<const mtmd_bitmap *> bitmaps;
diff --git a/tools/mtmd/mtmd.h b/tools/mtmd/mtmd.h
index f4ea07d3ad5..d743e52f5a4 100644
--- a/tools/mtmd/mtmd.h
+++ b/tools/mtmd/mtmd.h
@@ -96,6 +96,14 @@ MTMD_API mtmd_context * mtmd_init_from_file(const char * mmproj_fname,
 
 MTMD_API void mtmd_free(mtmd_context * ctx);
 
+// Set up logging to use llama's logging callback
+// This redirects all mtmd/clip logging through llama's logging system
+// Call this after llama_log_set to ensure mtmd uses the same logging callback
+// Example:
+//   llama_log_set(my_log_callback, my_user_data);
+//   mtmd_log_set_llama_callback(my_log_callback, my_user_data);
+MTMD_API void mtmd_log_set_llama_callback(ggml_log_callback llama_cb, void * llama_user_data);
+
 // whether we need to set non-causal mask before llama_decode
 MTMD_API bool mtmd_decode_use_non_causal(mtmd_context * ctx);