Update README.md

README.md

@@ -100,7 +100,7 @@ Even though the 7B INT8 model itself takes approximately **8–9 GB**, we recomm
 For pure CPU inference (no GPU), we recommend at least **64GB system RAM** (Ryzen 9 7950X/9950X).
 
 ---
-I adedd default model in FP32 about 62 Gb size for full precision for quatization to less size  .
+I added the default model in full FP32 precision, which is approximately 62 GB in size. This serves as the base for quantization, allowing us to find the optimal balance between model size and performance.
 
 
 ## 📧 Contact & Licensing