diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py
index eb8387c6ca..e97c5e3457 100644
--- a/studio/backend/core/inference/llama_cpp.py
+++ b/studio/backend/core/inference/llama_cpp.py
@@ -198,8 +198,11 @@ class LlamaCppBackend:
         """Query free memory per GPU via nvidia-smi.
 
         Returns list of (gpu_index, free_mib) sorted by index.
-        Returns empty list if nvidia-smi is not available.
+        Only returns GPUs that are allowed by CUDA_VISIBLE_DEVICES
+        (if set). Returns empty list if nvidia-smi is not available.
         """
+        import os
+
         try:
             result = subprocess.run(
                 [
@@ -213,12 +216,24 @@ class LlamaCppBackend:
             )
             if result.returncode != 0:
                 return []
+
+            # Parse which GPUs are allowed by existing CUDA_VISIBLE_DEVICES
+            allowed = None
+            cvd = os.environ.get("CUDA_VISIBLE_DEVICES")
+            if cvd is not None and cvd.strip():
+                try:
+                    allowed = set(int(x.strip()) for x in cvd.split(","))
+                except ValueError:
+                    pass  # Non-numeric (e.g., "GPU-uuid"), ignore filter
+
             gpus = []
             for line in result.stdout.strip().splitlines():
                 parts = line.split(",")
                 if len(parts) == 2:
                     idx = int(parts[0].strip())
                     free_mib = int(parts[1].strip())
+                    if allowed is not None and idx not in allowed:
+                        continue
                     gpus.append((idx, free_mib))
             return gpus
         except Exception: