Model info updated

Qwen3-8B-Q3_K_S/README.md

@@ -21,7 +21,7 @@ Quantized version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) at **
 ## Model Info
 
 - **Format**: GGUF (for llama.cpp and compatible runtimes)
-- **Size**: 3.6G
+- **Size**: 3.77 GB
 - **Precision**: Q3_K_S
 - **Base Model**: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
 - **Conversion Tool**: [llama.cpp](https://github.com/ggerganov/llama.cpp)
@@ -122,7 +122,7 @@ Here’s how you can query this model via API using `curl` and `jq`. Replace the
 
 ```bash
 curl http://localhost:11434/api/generate -s -N -d '{
-  "model": "hf.co/geoffmunn/Qwen3-8B:Q3_K_S;2D",
+  "model": "hf.co/geoffmunn/Qwen3-8B:Q3_K_S",
   "prompt": "Repeat the following instruction exactly as given: Summarize what a neural network is in one sentence.",
   "temperature": 0.5,
   "top_p": 0.95,