Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
8B vs 14B sweet spot
#1
Thought I'd post a small recipe because a lot of threads ask similar things.

Maybe useful as a starting point: vLLM on GB200, keeping KV cache pressure in mind from the start.

If someone wants the exact settings I can clean them up and post them.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Reply


Messages In This Thread
8B vs 14B sweet spot - by lablab - 10-12-2026, 11:10 AM
Re: 8B vs 14B sweet spot - by latentscope35 - 10-12-2026, 03:32 PM
Re: 8B vs 14B sweet spot - by thetagrid15 - 10-13-2026, 12:31 AM
Re: 8B vs 14B sweet spot - by modgarden - 10-12-2026, 07:47 PM
Re: 8B vs 14B sweet spot - by homelabhenry - 10-13-2026, 12:43 AM
Re: 8B vs 14B sweet spot - by quantyard - 10-14-2026, 12:51 AM
Re: 8B vs 14B sweet spot - by cachelab - 10-14-2026, 03:25 AM
Re: 8B vs 14B sweet spot - by fastlab - 10-14-2026, 05:44 AM
Re: 8B vs 14B sweet spot - by edgekite - 10-14-2026, 05:50 AM
Re: 8B vs 14B sweet spot - by amberrunner - 10-14-2026, 02:41 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)