Update usage to Osaurus branding

README.md

@@ -65,9 +65,13 @@ mlx-vlm's default quantization predicate automatically keeps MLP gate/up/down pr
 
 ## Usage
 
-### With mlx-vlm
+```bash
+# Requires Osaurus (https://osaurus.ai)
+osaurus serve OsaurusAI/gemma-4-E4B-it-4bit
+```
 
 ```python
+# Python API
 from mlx_vlm import load, generate
 
 model, processor = load("OsaurusAI/gemma-4-E4B-it-4bit")
@@ -79,12 +83,6 @@ output = generate(model, processor, "Explain quantum computing", max_tokens=500)
 output = generate(model, processor, "Describe this image", ["path/to/image.jpg"], max_tokens=500)
 ```
 
-### With vMLX / vllm-mlx
-
-```bash
-vllm-mlx serve OsaurusAI/gemma-4-E4B-it-4bit
-```
-
 ## Conversion Details
 
 | Detail | Value |