Welcome • User Guide
ToS • Privacy • Canary
Donate • Bugs • License

©2025 Poal.co

591

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).
[–] • 0 pt

I think 32/48GB will give decent results without swapping and wearing the SSD.

[–] • 0 pt

Apple M2 GPU cores 8–10 Apple M2 Pro GPU cores 30–38

As I see it, 3x at minimum

[–] • 0 pt

You haven't mentioned how much unified memory, which is an important point.

[–] • 0 pt

32gb unified memory.