Update README.md

README.md

@@ -102,9 +102,6 @@ license_name: llama4
   <p style="margin-bottom: 0; margin-top: 0;">
     <strong>See <a href="https://huggingface.co/collections/unsloth/llama-4-67f19503d764b0f3a2a868d2">our collection</a> for versions of Llama 4 including 4-bit & 16-bit formats.</strong>
   </p>
-  <p style="margin-bottom: 0;">
-    <em><a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4">Read our Guide</a> to see how to Fine-tune & Run Llama 4 correctly.</em>
-  </p>
   <div style="display: flex; gap: 5px; align-items: center; ">
     <a href="https://github.com/unslothai/unsloth/">
       <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
@@ -118,15 +115,18 @@ license_name: llama4
   </div>
 <h1 style="margin-top: 0rem;">✨ Run Unsloth Dynamic Llama 4!</h1>
 </div>
-
-|MoE Bits|Type|Disk Size|HF Link|
-|:-|:-|:-|:-|
-|1.78bit|IQ1\_S|**33.8GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF?show_file_info=Llama-4-Scout-17B-16E-Instruct-UD-IQ1_S.gguf)|
-|1.93bit|IQ1\_M|**35.4B**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF?show_file_info=Llama-4-Scout-17B-16E-Instruct-UD-IQ1_M.gguf)|
-|2.42-bit|IQ2\_XXS|**38.6GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF?show_file_info=Llama-4-Scout-17B-16E-Instruct-UD-IQ2_XXS.gguf)|
-|2.71-bit|Q2\_K\_XL|**42.2GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF?show_file_info=Llama-4-Scout-17B-16E-Instruct-UD-Q2_K_XL.gguf)|
-|3.5-bit|Q3\_K\_XL|**52.9GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/UD-IQ3_K_XL)|
-|4.5-bit|Q4\_K\_XL|**65.6GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/UD-IQ4_K_XL)|
+  <p style="margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4">Read our Guide</a> to see how to Fine-tune & Run Llama 4 correctly.</em>
+  </p>
+  
+|MoE Bits|Type|Disk Size|HF Link|Accuracy|
+|:-|:-|:-|:-|:-|
+|1.78bit|IQ1\_S|**33.8GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF?show_file_info=Llama-4-Scout-17B-16E-Instruct-UD-IQ1_S.gguf)|Ok|
+|1.93bit|IQ1\_M|**35.4B**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF?show_file_info=Llama-4-Scout-17B-16E-Instruct-UD-IQ1_M.gguf)|Fair|
+|2.42-bit|IQ2\_XXS|**38.6GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF?show_file_info=Llama-4-Scout-17B-16E-Instruct-UD-IQ2_XXS.gguf)|Better|
+|2.71-bit|Q2\_K\_XL|**42.2GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF?show_file_info=Llama-4-Scout-17B-16E-Instruct-UD-Q2_K_XL.gguf)|Suggested|
+|3.5-bit|Q3\_K\_XL|**52.9GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/UD-IQ3_K_XL)|Great|
+|4.5-bit|Q4\_K\_XL|**65.6GB**|[Link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF/tree/main/UD-IQ4_K_XL)|Best|
 
 - Fine-tune Llama-4-Scout on a single H100 80GB GPU using Unsloth!
 - Read our Blog about Llama 4 support: [unsloth.ai/blog/llama4](https://unsloth.ai/blog/llama4)