Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
embedding model you trust
#1
Did a bit of testing and thought I'd post the result here.

I tried this with Phi using SGLang on M3 Max. The headline result was better than I expected, but structured output still ended up being the limiting factor.

Nothing scientific here, just practical notes from a real setup.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
small models can still be good
Reply


Messages In This Thread
embedding model you trust - by localtinker - 09-09-2026, 05:24 AM
Re: embedding model you trust - by cudaline - 09-09-2026, 07:51 AM
Re: embedding model you trust - by kernelmike - 09-09-2026, 08:00 PM
Re: embedding model you trust - by pixelcrate82 - 09-12-2026, 08:40 PM
Re: embedding model you trust - by localpatch78 - 09-13-2026, 09:17 PM
Re: embedding model you trust - by sparrowgrid - 09-16-2026, 09:59 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)