Most efficient way to load machine learning model (.h5) into web app?

I have trained a tensorflow model and saved it in the form of a .h5 file, about the size of 700mb. What’s the most efficient way to load this into the web app. I have tried storing it on digitalOcean space, but loading is not very efficient, takes about over 45 seconds. Any tips for speeding this up? Below is the code I used to load the model.

def load():
    session1 = session.Session()
    client = session1.client('s3',
                            region_name='nyc3',
                            endpoint_url=DO_SPACES_ENDPOINT,
                            aws_access_key_id=DO_SPACES_ACCESS_KEY,
                            aws_secret_access_key=DO_SPACES_SECRET_KEY)

    model_object = client.get_object(Bucket=BUCKET_NAME, Key=WEIGHTS_FILE)
    model_content = model_object['Body'].read()
    with tempfile.NamedTemporaryFile(suffix='.h5', delete=False) as fp:
        fp.write(model_content)
        model_path = fp.name
    return model_path