Update README.md

README.md

@@ -52,7 +52,7 @@ print(response[0].outputs[0].text)
 
 ## 🏗️ Technical Specifications
 ### Hardware Requirements
-- **Inference**: 46GB VRAM (+ Context)
+- **Inference**: 47GB VRAM (+ Context)
 - **Supported GPUs**: H100, L40S, A100 (80GB), RTX 4090 (2x for tensor parallelism)
 - **GPU Architecture**: Ada Lovelace, Hopper (for optimal FP8 performance)
 ### Quantization Details