diff --git a/llama.cpp b/llama.cpp index 935130b63..f8f7c4bca 100644 --- a/llama.cpp +++ b/llama.cpp @@ -122,7 +122,7 @@ static const std::map & MEM_REQ_KV_SELF() static const std::map & MEM_REQ_EVAL() { static std::map k_sizes = { - { MODEL_3B, 512ull * MB }, + { MODEL_3B, 640ull * MB }, { MODEL_7B, 768ull * MB }, { MODEL_13B, 1024ull * MB }, { MODEL_30B, 1280ull * MB },