32gb unified memory.
32gb unified memory.
Do they still swap when running ~30b models?
Do they still swap when running ~30b models?
Anyone running this stuff? Just wondering. I don't know anyone with these running right now.
Archive: https://archive.today/FtDXp
From the post:
>I’m running a 24-billion parameter model on a Mac I bought in 2022, fully on-prem, fully under my control, powering an autonomous AI agent team through OpenClaw. The agents handle Slack, run research, draft content, monitor infrastructure, and spawn sub-agents for compound tasks. No API fees. No cloud provider. $1.50 a month in electricity. It took 14 errors, two hard freezes, and a week of patching OpenClaw’s source code to get here. This is everything I learned.
Anyone running this stuff? Just wondering. I don't know anyone with these running right now.
Archive: https://archive.today/FtDXp
From the post:
>>I’m running a 24-billion parameter model on a Mac I bought in 2022, fully on-prem, fully under my control, powering an autonomous AI agent team through OpenClaw. The agents handle Slack, run research, draft content, monitor infrastructure, and spawn sub-agents for compound tasks. No API fees. No cloud provider. $1.50 a month in electricity. It took 14 errors, two hard freezes, and a week of patching OpenClaw’s source code to get here. This is everything I learned.
You are currently inside a comment thread.
Click here to see all the comments (14).