diff --git a/comfy/samplers.py b/comfy/samplers.py
index ab691ed5b..1ff50f51d 100755
--- a/comfy/samplers.py
+++ b/comfy/samplers.py
@@ -444,6 +444,7 @@ def _calc_cond_batch_multigpu(model: BaseModel, conds: list[list[dict]], x_in: t
 
     def _handle_batch(device: torch.device, batch_tuple: tuple[comfy.hooks.HookGroup, tuple], results: list[thread_result]):
         try:
+            torch.cuda.set_device(device)
             model_current: BaseModel = model_options["multigpu_clones"][device].model
             # run every hooked_to_run separately
             with torch.no_grad():