| ▲ | amelius 3 hours ago |
| How many tokens per second would you even get on them? |
|
| ▲ | kennywinker 3 hours ago | parent | next [-] |
| Afaik most openclaw users aren’t running their llm locally - just using a mac mini as an always-on sandbox for agents. |
| |
| ▲ | copperx 3 hours ago | parent | next [-] | | Cool, like a $5 VPS? | | |
| ▲ | o_m an hour ago | parent | next [-] | | A $5 VPS is easy to block. It's way harder to block a stock mac mini from a residential IP address | | |
| ▲ | DaSHacka an hour ago | parent [-] | | But why a Mac mini over a $30 raspberry pi on the same residential connection? |
| |
| ▲ | kennywinker 2 hours ago | parent | prev [-] | | Yes, but 100 times more expensive. |
| |
| ▲ | xhkkffbf 3 hours ago | parent | prev [-] | | A sandbox with access to iMessage. Can't have your agent texting with green boxes. | | |
|
|
| ▲ | simonh 3 hours ago | parent | prev [-] |
| 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. |