Anyone have a sense for system requirements on running this locally? StableDiffusion was too heavy for either of my machines (which are admittedly not very powerful) - I'm not seeing much in the docs to indicate whether or not this is more or less intensive to run locally.
If you can run any models on llama.cpp, that might be a good indicator of which StableLM models you'll be able to run.
I easily ran 7B int 4 ggml models on an MBP with 16gig RAM. Same works on a MBA with 8 gig RAM, but you'll have to not run any other memory-hogging app.
