[wannabeKazakh]

when you say run what actually do you mean?

if you can install transformers to your imac, the easiest way is to just check in code real quick, so just run the transformers code to load the model and tokenizer. Start with some basic bert models and move up. if you try to use a model loader app esp with full interface app like textgen or lm studio, you're adding overhead. ollama model server/loader is quite fast to me likely because it only comes with cli interface out of the box but it doesn't support all models and the smallest model is a quantized orca-mini which is unlikely to work for you.