Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
vision-language models on consumer gear
#14
Quote:[quote][quote]Interesting, I hadn't tried that. That matches what I saw on GB200. The biggest change for me was simplifying the stack instead of addin

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?
small models can still be useful
Reply


Messages In This Thread
Re: vision-language models on consumer gear - by quiettoken - 10-19-2026, 02:09 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)