Again, I would not argue against any of this.
And I can't say that I won't switch to openrouter (even just for the same models) at some point.
But one of the things I have found about my own process learning is that some lessons only come to you when you make yourself available to them. And if that means doing things the difficult way, that is what you should do.
Difficult... and wastefully expensive
Seems like an investment into building expertise, which is likely to have high ROI in the future, rather than a wasteful cost.
I mean, it's a (secondhand) computer I bought for other tasks (processing very large photos, compiling large apps quickly). It's running all the time. It can also run LLMs when I want to.
The rest of my life is ultra-frugal so I am relaxed about this.
Don't bite. You're right.
Having spent a good weekend learning how to perform latent-steering through playing with pytorch and a local Gemma4 model, there is no way I could have groked any of that in the the way I did without hands on time.
This is on an M3 Max 36GB I've had for a couple of years. No further outlay needed.
My thinking is totally aligned with yours, perhaps its because I am trying to do a second act at almost 50 from blue-collar to white collar office work. I have no formal degree, but I have been hobby programming for 20 years. I have made a habit of "letting myself be available to all lessons"... the localllama group has made this journey really fun if nothing else. I have learned an ABSOLUTE ton from this era!
I have been contemplating a move in the opposite direction because I have just been exhausted and depressed, so for me, really learning this stuff this way has been about managing those feelings, about a sense of pride and ownership of my processes.
I don't know if it has changed my mind about a career change but as I am sure you can understand, I no longer feel like I am running away defeated.
My very best wishes to you :-)
People pay thousands for model trains, everyone needs a hobby.
Training models vs modelling trains
Ah yes, the EMD0E9-30B-Union-Pacific.gguf
I'm sending Codex-gpt-5.5-cyber.stl to my printer right now!