Update README.md

README.md

@@ -22,6 +22,25 @@ This is an FP8 dynamically quantized (W8A8) version of `OpenGVLab/InternVL3_5-38
 
 The quantization process uses a specialized recipe that preserves the model's core visual understanding capabilities while reducing the memory footprint by nearly 50%.
 
+## Just Run It (vLLM serve)
+
+You can serve the model using vLLM's OpenAI-compatible API server.
+
+```bash
+vllm serve brandonbeiler/InternVL3_5-38B-FP8-Dynamic \
+    --quantization compressed-tensors \
+    --served-model-name internvl3_5-38b \
+    --reasoning-parser: qwen3 \
+    --trust-remote-code \
+    --max-model-len 32768 \
+    --tensor-parallel-size 1 # Adjust based on your GPU setup
+```
+**Notes**
+- 32k max context length
+- reasoning parser ready to go, requires system prompt to run in thinking mode
+- still investigating tool calling
+
+
 ## Key Features
 
 *   **Calibration-Free FP8:** Dynamic W8A8 quantization. Weights are pre-quantized, and activations are quantized on the fly.
@@ -40,19 +59,6 @@ The quantization process uses a specialized recipe that preserves the model's co
 | **Quantization Library** | [LLM Compressor](https://github.com/vllm-project/llm-compressor) v0.7.1 |
 | **Quantized By** | [brandonbeiler](https://huggingface.co/brandonbeiler) |
 
-## With vLLM OpenAI-Compatible Server
-
-You can serve the model using vLLM's OpenAI-compatible API server.
-
-```bash
-vllm serve brandonbeiler/InternVL3_5-38B-FP8-Dynamic \
-    --quantization compressed-tensors \
-    --served-model-name internvl3_5-38b \
-    --reasoning-parser: qwen3 \
-    --trust-remote-code \
-    --max-model-len 32768 \
-    --tensor-parallel-size 1 # Adjust based on your GPU setup
-```
 
 ## Usage with vLLM in Python