Update README.md

README.md

@@ -5,4 +5,6 @@ license: other
 ---
 
 This is a [ggml](https://github.com/ggerganov/ggml/) quantized version of [Replit-v2-CodeInstruct-3B](https://huggingface.co/teknium/Replit-v2-CodeInstruct-3B). Quantized to 4bit -> q4_1.
-To run inference you can use ggml directly or ctransformers (bindings/demo repo to be added): https://github.com/marella/ctransformers
+To run inference you can use ggml directly or ctransformers (bindings/demo repo to be added): https://github.com/marella/ctransformers.
+
+Memory usage of model: **2GB~**