Check hf_cache for mlx models

llms/mlx_lm/server.py

@@ -11,6 +11,7 @@ from pathlib import Path
 from typing import Dict, List, Literal, NamedTuple, Optional, Sequence, Union
 
 import mlx.core as mx
+from huggingface_hub import scan_cache_dir
 
 from .utils import generate_step, load
 
@@ -635,13 +636,21 @@ class APIHandler(BaseHTTPRequestHandler):
         """
         self._set_completion_headers(200)
         self.end_headers()
+
+        # Scan the cache directory for downloaded mlx models
+        hf_cache_info = scan_cache_dir()
+        downloaded_models = [
+            repo for repo in hf_cache_info.repos if "mlx" in repo.repo_id
+        ]
+
         # Create a list of available models
         models = [
             {
-                "id": self.model_provider.cli_args.model,
+                "id": repo.repo_id,
                 "object": "model",
                 "created": self.created,
             }
+            for repo in downloaded_models
         ]
 
         response = {"object": "list", "data": models}