Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
structured output failures
#1
I'm trying to sanity-check my setup.

My current setup is Ollama with A6000, and I keep running into token cost.

If you've tested something similar, what did you keep and what did you stop bothering with?
mostly local
Reply
#2
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at workstation thermals. Not glamorous advice, but repeatable baselines save a lot of time.
trying not to rebuild again
Reply
#3
Interesting, I hadn't tried that. That matches what I saw on 4090.
curious and caffeinated
Reply
#4
Appreciate the detail. That matches what I saw on A6000.
Reply
#5
Quote:Appreciate the detail. That matches what I saw on A6000.

I hit almost the same issue last night.
Reply
#6
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
learning in public
Reply
#7
subscribed, curious where this lands.
Reply
#8
Thanks, that helps. I don't think your conclusion is far off.
trying not to rebuild again
Reply
#9
Interesting, I hadn't tried that. That matches what I saw on dual 3090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
routing beats arguing over one perfect model
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)