diff --git a/docs/build.md b/docs/build.md
index 9e44f18eae..e2af1b96dd 100644
--- a/docs/build.md
+++ b/docs/build.md
@@ -754,7 +754,7 @@ git switch dev_backend_openvino
 
 # Build with OpenVINO support
 source /opt/intel/openvino/setupvars.sh
-cmake -B build/ReleaseOV -G Ninja -DCMAKE_BUILD_TYPE=Release -DGGML_OPENVINO=ON
+cmake -B build/ReleaseOV -G Ninja -DCMAKE_BUILD_TYPE=Release -DGGML_OPENVINO=ON -DGGML_CPU_REPACK=OFF
 cmake --build build/ReleaseOV --config Release -j $(nproc)
 ```
 
diff --git a/ggml/src/ggml-openvino/ggml-decoder.cpp b/ggml/src/ggml-openvino/ggml-decoder.cpp
index a3e7059fa2..cd897e5f68 100644
--- a/ggml/src/ggml-openvino/ggml-decoder.cpp
+++ b/ggml/src/ggml-openvino/ggml-decoder.cpp
@@ -432,6 +432,10 @@ std::shared_ptr<ov::Node> GgmlOvDecoder::create_weight_node(ggml_tensor* tensor)
     }
 
     // Quantized case
+    OPENVINO_ASSERT(
+        tensor->extra == nullptr,
+        "Unsupported weight tensor: " + std::string(tensor->name) + " Possibly this is a repacked quantized weights");
+
     node_shape.erase(node_shape.begin());
 
     uint64_t weights_per_byte;
diff --git a/ggml/src/ggml-openvino/ggml-openvino.cpp b/ggml/src/ggml-openvino/ggml-openvino.cpp
index f81b1ee483..23a92c58ac 100644
--- a/ggml/src/ggml-openvino/ggml-openvino.cpp
+++ b/ggml/src/ggml-openvino/ggml-openvino.cpp
@@ -420,8 +420,7 @@ static bool ggml_backend_openvino_device_supports_op(ggml_backend_dev_t dev, con
 }
 
 static bool ggml_backend_openvino_device_supports_buft(ggml_backend_dev_t dev, ggml_backend_buffer_type_t buft) {
-    // TODO quantized weigts are cpu_repack_buffer_type which does not implement ggml_backend_buft_is_host
-    return ggml_backend_buft_is_host(buft) || strcmp(buft->device->iface.get_name(buft->device), "CPU") == 0;
+    return ggml_backend_buft_is_host(buft);
     GGML_UNUSED(dev);
 }