Update README.md

README.md

@@ -24,6 +24,9 @@ TRURL 2 is a collection of fine-tuned generative text models with 7 billion and
 
 This is the repository for the 7b fine-tuned QUANTIZED model 8-bit, optimized for dialogue use cases.
 Quantization results in a significantly smaller and faster model at a cost of slightly (or sometimes considerably) worse results, depending on the size reduction and provided input.
+
+This models takes around 8Gb of GPU RAM.
+
 If you need a full version check it here: 
 * [TRURL 13b](https://huggingface.co/Voicelab/trurl-2-13b/)
 * [TRURL 7b](https://huggingface.co/Voicelab/trurl-2-7b/)