Update README.md

README.md

@@ -1,4 +1,5 @@
 ---
 license: llama3
 ---
-The Meta-Llama-3-8B-Instruct model quantized with 4 Bits. Tested on Raspberry PI Model 4 with [llama.cpp](https://github.com/ggerganov/llama.cpp). 
+## Quantized Meta-Llama-3B-Instruct model
+Tested inference on Raspberry PI Model 4 with [llama.cpp](https://github.com/ggerganov/llama.cpp). ~0.5 Tokens per second.