Machine learning container throws out of memory exception

[vs30217]

I am using immich server v.1.117.0 with buffalo_l model for facial recognition feature. I am having nvidia vgpu having 8G memory but still ML container keeps on throwing the out of memory exception-
RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION: Non zero status code returned while running Conv node. Name: 'Conv_5' status message: '/onnxruntime_src/onnxruntime/core/framework/bfc_arena.cc:376 void* onnxruntime:: BFCArena::AllocateRawInternal(size_t,bool,onnxruntime::Stream*,bool,onnxruntime::WaitNotificationFn) Failed to allocate memory for requested buffer of size 72253440 .

nvidia-smi output shows GPU memory usage- 7301 MiB