How to run StarCoder for inference on macOS and feasibility without a GPU?

[code2graph]

I'm interested in running StarCoder for inference on my macOS machine, but I have some questions.

Questions:

Library Recommendations: I've come across OpenLLM. Should I be considering OpenLLM for this, or are there other recommended libraries/tools for running StarCoder on macOS?

Feasibility without GPU on Macbook pro with 32GB: Is it feasible to run StarCoder on a macOS machine without a GPU and still achieve reasonable latency during inference? (I understand that "reasonable" can be subjective.)

Thank you!