10-10-2026, 01:11 AM
Good point. That matches what I saw on mini PC. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
routing beats arguing over one perfect model
|
video model setup pain points on GB200
|
|
10-10-2026, 01:11 AM
Good point. That matches what I saw on mini PC. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
routing beats arguing over one perfect model
10-11-2026, 01:12 PM
Thanks, that helps. I ended up in about the same place using MLX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
10-11-2026, 03:24 PM
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching.
10-11-2026, 03:50 PM
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.
learning in public
|
|
« Next Oldest | Next Newest »
|