Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 - llama-cpp
 - imatrix
 - gguf
-- Q8_0
+- IQ4_NL
 - 3b
 - SmallThinker
 - qwen
@@ -31,16 +31,16 @@ tags:
 # roleplaiapp/SmallThinker-3B-Preview-IQ4_NL-GGUF
 
 **Repo:** `roleplaiapp/SmallThinker-3B-Preview-IQ4_NL-GGUF`  
-**Original Model:** `imatrix`
+**Original Model:** `SmallThinker-3B-Preview`
 **Organization:** `PowerInfer`
-**Quantized File:** `smallthinker-3b-preview-iq4_nl-imat.gguf`
+**Quantized File:** `smallthinker-3b-preview-iq_4nl-imat.gguf`
 **Quantization:** `GGUF`
-**Quantization Method:** `Q8_0`  
+**Quantization Method:** `IQ4_NL`  
 **Use Imatrix:** `True`  
 **Split Model:** `False`
 
 ## Overview
-This is an GGUF Q8_0 quantized version of [imatrix](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview).
+This is an imatrix GGUF IQ4_NL quantized version of [SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview).
 
 ## Quantization By
 I often have idle A100 GPUs while building/testing and training the RP app, so I put them to use quantizing models.