is there any way to stop this moving model thing

[l33tx0]

each time this take around 10-15 seconds while image generation itself take 30 sec for 20 step on a 3080 ti card fp8 quant flux this happens each time if i generate in batch or single single

Moving model(s) has taken 10.72 seconds 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:28<00:00, 1.42s/it] [Unload] Trying to free 4563.84 MB for cuda:0 with 0 models keep loaded ... Current free memory is 1877.96 MB ... Unload model KModel Done.█████████████████████████████████████████████████████████| 20/20 [00:28<00:00, 1.49s/it] [Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 10957.89 MB, Model Require: 159.87 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9774.01 MB, All loaded to GPU. Moving model(s) has taken 4.50 seconds