|
|
|
|
|
|
by ericd
2 hours ago
|
|
|
Half of my point was to test the models, the other half was to try to get a sense of what the speed would be. Hard to do, but dropping $5k on a 128 gig machine thinking that will unlock good local AI and then realizing that you’ll need to spend >$20k more to run a decent model, and then finding out that even that gives you crap speed isn’t the best way to discover all this. I very much want local AI to win this in the end, but it’s extremely expensive to run good models at good speed locally right now. Minimax M2.5/2.7, Qwen 3.6, etc are pretty good for basic stuff, but pretty far off from competing with Opus/Fable. |
|
|