I’m a bit weary about posting this cos the last time I boasted about my Hermes Agent it crashed and it took me a week to get it back up. But I’m bursting and need to share.
So I’ve got a MacStudio 36GB and I’m running Hermes Agent with gemma4:31b locally with ollama and now I’ve added qwen3-vl for ‘vision’ also locally on ollama. But what I’m most proud of is the Apple account for this computes is registered to my agent (used
@Proton Mail and
https://sms4sats.com/ for the sms - used Netherlands). I’ve then got GitHub via Apple ID, agent Mail, signal, and various things linked to my agent only. I’ve set up a skill where my agent upgrades to
@Maple for complex things. I also used
@PayPerQ to run Hermes using opus 4.8 which burned through money and didn’t achieve much. Gemma4 takes time but it gets it right. Much better than GLM-4.7 which I was running earlier.
Now I just need to figure what to do with all this power.
Done. Feeling better. Thanks for listening.