Update README.md

README.md

@@ -29,11 +29,11 @@ pip install mlx-lm
 You can use `mlx-lm` from the command line. For example:
 
 ```
-mlx_lm.generate --model mlx-community/Mistral-7B-Instruct-v0.3-4bit --prompt "hello"
+mlx_lm.generate --model mlx-community/Qwen3-4B-Instruct-2507-4bit --prompt "hello"
 ```
 
-This will download a Mistral 7B model from the Hugging Face Hub and generate
-text using the given prompt. 
+This will download a Qwen3 4B model from the Hugging Face Hub and generate
+text using the given prompt.
 
 To chat with an LLM use:
 
@@ -55,7 +55,7 @@ mlx_lm.chat --help
 To quantize a model from the command line run:
 
 ```
-mlx_lm.convert --hf-path mistralai/Mistral-7B-Instruct-v0.3 -q 
+mlx_lm.convert --model Qwen/Qwen3-4B-Instruct-2507 -q 
 ```
 
 For more options run:
@@ -65,14 +65,14 @@ mlx_lm.convert --help
 ```
 
 You can upload new models to Hugging Face by specifying `--upload-repo` to
-`convert`. For example, to upload a quantized Mistral-7B model to the 
+`convert`. For example, to upload a quantized Qwen3 4B model to the 
 [MLX Hugging Face community](https://huggingface.co/mlx-community) you can do:
 
 ```
 mlx_lm.convert \
-    --hf-path mistralai/Mistral-7B-Instruct-v0.3 \
+    --model Qwen/Qwen3-4B-Instruct-2507 \
     -q \
-    --upload-repo mlx-community/my-4bit-mistral
+    --upload-repo mlx-community/Qwen3-4B-Instruct-2507-4bit
 ```
 
 Models can also be converted and quantized directly in the