初始化项目，由ModelHub XC社区提供模型

Model: jedisct1/Qwen3-4B-Thinking-2507-mlx
Source: Original Platform

README.md

@@ -0,0 +1,37 @@
+---
+library_name: mlx
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model: Qwen/Qwen3-4B-Thinking-2507
+tags:
+- mlx
+---
+
+# jedisct1/Qwen3-4B-Thinking-2507-mlx
+
+This model [jedisct1/Qwen3-4B-Thinking-2507-mlx](https://huggingface.co/jedisct1/Qwen3-4B-Thinking-2507-mlx) was
+converted to MLX format from [Qwen/Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507)
+using mlx-lm version **0.26.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("jedisct1/Qwen3-4B-Thinking-2507-mlx")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```