diff --git a/ggml-cuda/fattn-tile-f32.cu b/ggml-cuda/fattn-tile-f32.cu
index 54db765e2..b8b2f69e1 100644
--- a/ggml-cuda/fattn-tile-f32.cu
+++ b/ggml-cuda/fattn-tile-f32.cu
@@ -283,8 +283,7 @@ void launch_fattn_tile_f32_64_128(ggml_backend_cuda_context & ctx, ggml_tensor *
 }
 
 void ggml_cuda_flash_attn_ext_tile_f32(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
-    const ggml_tensor * KQV = dst;
-    const ggml_tensor * Q   = dst->src[0];
+    const ggml_tensor * Q = dst->src[0];
 
     if (Q->ne[1] <= 16) {
         constexpr int cols_per_block = 16;
diff --git a/llama.cpp b/llama.cpp
index 0a587d4cb..62964cfb7 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -3793,12 +3793,14 @@ static std::string llama_model_ftype_name(llama_ftype ftype) {
 
 static const char * llama_model_type_name(e_model type) {
     switch (type) {
+        case MODEL_17M:    return "17M";
         case MODEL_22M:    return "22M";
         case MODEL_33M:    return "33M";
         case MODEL_70M:    return "70M";
         case MODEL_109M:   return "109M";
         case MODEL_137M:   return "137M";
         case MODEL_160M:   return "160M";
+        case MODEL_335M:   return "335M";
         case MODEL_410M:   return "410M";
         case MODEL_0_5B:   return "0.5B";
         case MODEL_1B:     return "1B";
@@ -3806,6 +3808,7 @@ static const char * llama_model_type_name(e_model type) {
         case MODEL_2B:     return "2B";
         case MODEL_2_8B:   return "2.8B";
         case MODEL_3B:     return "3B";
+        case MODEL_4B:     return "4B";
         case MODEL_6_9B:   return "6.9B";
         case MODEL_7B:     return "7B";
         case MODEL_8B:     return "8B";