How many tokens per second would you even get on them?
Afaik most openclaw users aren’t running their llm locally - just using a mac mini as an always-on sandbox for agents.
OpenClaw was originally designed to run on a Mac, but using remote LLMs accessed via API. Running the LLM locally on beefier hardware came later.
Afaik most openclaw users aren’t running their llm locally - just using a mac mini as an always-on sandbox for agents.