Update app.py

app.py

@@ -329,11 +329,10 @@ ONLY WORKS WITH GPU!
 You can load the model with 8-bit or 4-bit quantization to make it fit in smaller hardwares. Setting the environment variable `bits` to control the quantization.
 
 Recommended configurations:
-| Hardware           | Bits           |
-|--------------------|----------------|
-| A10G-Large (24G)   | 8 (default)    |
-| T4-Medium (16G)    | 4              |
-| A100-Large (40G)   | 16             |
+| Hardware          | A10G-Large (24G) | T4-Medium (15G) | A100-Large (40G) |
+|-------------------|------------------|-----------------|------------------|
+| **Bits**          | 8 (default)      | 4               | 16               |
+
 """
 
 tos_markdown = """