diff --git a/ggml-cuda/mmq.cuh b/ggml-cuda/mmq.cuh
index f97bbd6e7..d59c0532f 100644
--- a/ggml-cuda/mmq.cuh
+++ b/ggml-cuda/mmq.cuh
@@ -8,7 +8,6 @@
 #include <cstdint>
 
 #define MMQ_DP4A_MAX_BATCH_SIZE 64 // Max. batch size to use for dp4a MMQ kernels when FP16 tensor cores are available.
-#define GGML_CUDA_FORCE_MMQ
 
 typedef void (*load_tiles_mmq_t)(const char * __restrict__ x, int * x_tile, const int & kbx0, const int & i_max, const int & stride);
 typedef void (*vec_dot_mmq_t)(const int * __restrict__ x, const int * __restrict__ y, float * __restrict__ sum, const int & k0);