Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
frankenmerges anyone kept using with MLX
#1
Posting this in case it saves someone else a little time.

If you were starting from scratch today for this use case, what would you choose first and what would you ignore?

Simple and boring is a valid answer.
Reply
#2
Quote:Posting this in case it saves someone else a little time.

Good point. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Reply
#3
What worked for me was pretty simple. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
small models can still be good
Reply
#4
that fixed it for me too. I keep promising myself this is the last rebuild.
Reply
#5
I'd approach it in a boring order. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
still benchmarking everything
Reply
#6
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal.
watching release notes so you don't have to
Reply
#7
subscribed, curious where this lands.
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)