diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index 2bce5c3485..e505ef40c2 100644
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -320,7 +320,7 @@ llama_context::llama_context(
 
         reserve();
 
-        if (cparams.flash_attn) {
+        if (!cparams.flash_attn) {
             if (ggml_is_quantized(params.type_v)) {
                 throw std::runtime_error("quantized V cache was requested, but this requires Flash Attention");
             }