i want a LLM CLI tool that only supports one model, a small CPU-ready 360M-1B...

i want a LLM CLI tool that only supports one model, a small CPU-ready 360M-1B model that spends almost none of its parameters on knowledge and always leans on external tools for knowledge & reasoning. wire this up as a CLI tool, phone app, etc. Make it an agent, ready to run for a long time. Go

i tend to think this is the direction they’re going with Apple Intelligence, but progress seems slow

mobile OS’s seem like a better place to experiment with this stuff, because they seem properly sandboxed by default, less to go wrong