Update README.md

README.md

@@ -298,7 +298,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <th>Docstring Generation<br>prefill: 768 tokens<br>decode: 128 tokens</th>
     <th>Code Fixing<br>prefill: 1024 tokens<br>decode: 1024 tokens</th>
     <th>RAG<br>prefill: 1024 tokens<br>decode: 128 tokens</th>
-    <th>baseion Following<br>prefill: 256 tokens<br>decode: 128 tokens</th>
+    <th>Instruction Following<br>prefill: 256 tokens<br>decode: 128 tokens</th>
     <th>Multi-turn Chat<br>prefill: 512 tokens<br>decode: 256 tokens</th>
     <th>Large Summarization<br>prefill: 4096 tokens<br>decode: 512 tokens</th>
   </tr>
@@ -326,7 +326,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>4.7</td>
   </tr>
   <tr>
-    <td>granite-3.1-2b-base-quantized.w8a8</td>
+    <td>granite-3.1-2b-base-quantized.w4a16</td>
     <td>1.94</td>
     <td>5.4</td>
     <td>0.7</td>
@@ -360,7 +360,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>4.5</td>
   </tr>
   <tr>
-    <td>granite-3.1-2b-base-quantized.w8a8</td>
+    <td>granite-3.1-2b-base-quantized.w4a16</td>
     <td>1.87</td>
     <td>5.1</td>
     <td>0.7</td>
@@ -417,7 +417,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>1.4</td>
   </tr>
   <tr>
-    <td>granite-3.1-2b-base-quantized.w8a8</td>
+    <td>granite-3.1-2b-base-quantized.w4a16</td>
     <td>0.98</td>
     <td>2.8</td>
     <td>10.0</td>
@@ -451,7 +451,7 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>1.7</td>
   </tr>
   <tr>
-    <td>granite-3.1-2b-base-quantized.w8a8</td>
+    <td>granite-3.1-2b-base-quantized.w4a16</td>
     <td>0.95</td>
     <td>3.7</td>
     <td>11.4</td>
@@ -462,4 +462,3 @@ guidellm --model neuralmagic/granite-3.1-2b-base-quantized.w8a8 --target "http:/
     <td>1.4</td>
   </tr>
 </table>
-