fix: Update selector to check available quantizations on Mac

src/models/selector.py

@@ -215,12 +215,15 @@ def select_optimal_model(
     available_vram, available_ram = get_available_memory_with_offload(hardware, offload_percent)
     
     # Get models to try (with appropriate quantizations)
+    # On Mac, check which quantizations are actually available
+    check_available = use_mlx
+    
     if preferred_model:
         from models.registry import get_model
-        preferred = get_model(preferred_model, use_mlx=use_mlx)
+        preferred = get_model(preferred_model, use_mlx=use_mlx, check_available=check_available)
         models = [preferred] if preferred else []
     else:
-        models = list_models(use_mlx=use_mlx)
+        models = list_models(use_mlx=use_mlx, check_available=check_available)
     
     # Note: On Apple Silicon with MLX, multiple instances work fine in sequential mode
     # The swarm manager will handle sequential execution to avoid GPU conflicts