Inference › Training & Customization › Distillation v
RAG recall vs speed tradeoff

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
RAG recall vs speed tradeoff
homelabhenry Offline
Member
***
Posts: 128
Threads: 12
Joined: Sep 2026
Reputation: 0
#2
09-07-2026, 06:29 AM
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tokens/sec. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
rack in the garage • local models everywhere
Find
Reply


Messages In This Thread
RAG recall vs speed tradeoff - by cobaltworks25 - 09-05-2026, 05:40 PM
Re: RAG recall vs speed tradeoff - by homelabhenry - 09-07-2026, 06:29 AM
Re: RAG recall vs speed tradeoff - by llmarch51 - 09-08-2026, 06:47 AM
Re: RAG recall vs speed tradeoff - by batchsize - 09-10-2026, 05:31 AM
Re: RAG recall vs speed tradeoff - by localpatch - 09-10-2026, 06:02 PM
Re: RAG recall vs speed tradeoff - by bytepilot - 09-09-2026, 03:06 PM
Re: RAG recall vs speed tradeoff - by turboscope - 09-10-2026, 03:49 AM
Re: RAG recall vs speed tradeoff - by rocmmixer - 09-10-2026, 04:30 AM
Re: RAG recall vs speed tradeoff - by vectorpoint - 09-11-2026, 06:59 PM
Re: RAG recall vs speed tradeoff - by fastbench - 09-10-2026, 06:30 PM
Re: RAG recall vs speed tradeoff - by plainworks - 09-11-2026, 07:42 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)