Typically you need about 1GB graphics RAM for each billion parameters (i.e. one byte per parameter). This is a 405B parameter model. Ouch.
Edit: you can try quantizing it. This reduces the amount of memory required per parameter to 4 bits, 2 bits or even 1 bit. As you reduce the size, the performance of the model can suffer. So in the extreme case you might be able to run this in under 64GB of graphics RAM.
It is terribly sad - they must live in a world of hurt.
However so many of these people actively try to hurt LGBTQ+ and trans people by inciting hate and changing laws to harm the non-straight. In particular they have been preaching that being gay/trans equates to being a child molester. This is horrific and needs to stop. Exposing the hypocrisy is essential to reducing the harm they are inflicting to real people right now