Update README.md

Author: ggerganov

README.md

@@ -5,6 +5,8 @@ Inference of [Facebook's LLaMA](https://github.com/facebookresearch/llama) model
 **TEMPORARY NOTICE:**
 If you observe garbage results, make sure to update to latest master. There was a bug and it was fixed here: https://github.com/ggerganov/llama.cpp/commit/70bc0b8b15b98dca23b28f0c8f5e34b27e424cda
 
+Also, currently the quantized models run **only** on Apple Silicon. On other architectures, you can [use the F16 models](https://github.com/ggerganov/llama.cpp/issues/2#issuecomment-1464615286), but they will be much slower. Support will be [added later](https://github.com/ggerganov/ggml/pull/27)
+
 ## Description
 
 The main goal is to run the model using 4-bit quantization on a MacBook.